arXiv daily

Computer Vision and Pattern Recognition (cs.CV)

Wed, 19 Apr 2023

Other arXiv digests in this category:Thu, 14 Sep 2023; Wed, 13 Sep 2023; Tue, 12 Sep 2023; Mon, 11 Sep 2023; Fri, 08 Sep 2023; Tue, 05 Sep 2023; Fri, 01 Sep 2023; Thu, 31 Aug 2023; Wed, 30 Aug 2023; Tue, 29 Aug 2023; Mon, 28 Aug 2023; Fri, 25 Aug 2023; Thu, 24 Aug 2023; Wed, 23 Aug 2023; Tue, 22 Aug 2023; Mon, 21 Aug 2023; Fri, 18 Aug 2023; Thu, 17 Aug 2023; Wed, 16 Aug 2023; Tue, 15 Aug 2023; Mon, 14 Aug 2023; Fri, 11 Aug 2023; Thu, 10 Aug 2023; Wed, 09 Aug 2023; Tue, 08 Aug 2023; Mon, 07 Aug 2023; Fri, 04 Aug 2023; Thu, 03 Aug 2023; Wed, 02 Aug 2023; Tue, 01 Aug 2023; Mon, 31 Jul 2023; Fri, 28 Jul 2023; Thu, 27 Jul 2023; Wed, 26 Jul 2023; Tue, 25 Jul 2023; Mon, 24 Jul 2023; Fri, 21 Jul 2023; Thu, 20 Jul 2023; Wed, 19 Jul 2023; Tue, 18 Jul 2023; Mon, 17 Jul 2023; Fri, 14 Jul 2023; Thu, 13 Jul 2023; Wed, 12 Jul 2023; Tue, 11 Jul 2023; Mon, 10 Jul 2023; Fri, 07 Jul 2023; Thu, 06 Jul 2023; Wed, 05 Jul 2023; Tue, 04 Jul 2023; Mon, 03 Jul 2023; Fri, 30 Jun 2023; Thu, 29 Jun 2023; Wed, 28 Jun 2023; Tue, 27 Jun 2023; Mon, 26 Jun 2023; Fri, 23 Jun 2023; Thu, 22 Jun 2023; Wed, 21 Jun 2023; Tue, 20 Jun 2023; Fri, 16 Jun 2023; Thu, 15 Jun 2023; Tue, 13 Jun 2023; Mon, 12 Jun 2023; Fri, 09 Jun 2023; Thu, 08 Jun 2023; Wed, 07 Jun 2023; Tue, 06 Jun 2023; Mon, 05 Jun 2023; Fri, 02 Jun 2023; Thu, 01 Jun 2023; Wed, 31 May 2023; Tue, 30 May 2023; Mon, 29 May 2023; Fri, 26 May 2023; Thu, 25 May 2023; Wed, 24 May 2023; Tue, 23 May 2023; Mon, 22 May 2023; Fri, 19 May 2023; Thu, 18 May 2023; Wed, 17 May 2023; Tue, 16 May 2023; Mon, 15 May 2023; Fri, 12 May 2023; Thu, 11 May 2023; Wed, 10 May 2023; Tue, 09 May 2023; Mon, 08 May 2023; Fri, 05 May 2023; Thu, 04 May 2023; Wed, 03 May 2023; Tue, 02 May 2023; Mon, 01 May 2023; Fri, 28 Apr 2023; Thu, 27 Apr 2023; Wed, 26 Apr 2023; Tue, 25 Apr 2023; Mon, 24 Apr 2023; Fri, 21 Apr 2023; Thu, 20 Apr 2023; Tue, 18 Apr 2023; Mon, 17 Apr 2023; Fri, 14 Apr 2023; Thu, 13 Apr 2023; Wed, 12 Apr 2023; Tue, 11 Apr 2023; Mon, 10 Apr 2023
1.Boosting Semantic Segmentation with Semantic Boundaries

Authors:Haruya Ishikawa, Yoshimitsu Aoki

Abstract: In this paper, we present the Semantic Boundary Conditioned Backbone (SBCB) framework, a simple yet effective training framework that is model-agnostic and boosts segmentation performance, especially around the boundaries. Motivated by the recent development in improving semantic segmentation by incorporating boundaries as auxiliary tasks, we propose a multi-task framework that uses semantic boundary detection (SBD) as an auxiliary task. The SBCB framework utilizes the nature of the SBD task, which is complementary to semantic segmentation, to improve the backbone of the segmentation head. We apply an SBD head that exploits the multi-scale features from the backbone, where the model learns low-level features in the earlier stages, and high-level semantic understanding in the later stages. This head perfectly complements the common semantic segmentation architectures where the features from the later stages are used for classification. We can improve semantic segmentation models without additional parameters during inference by only conditioning the backbone. Through extensive evaluations, we show the effectiveness of the SBCB framework by improving various popular segmentation heads and backbones by 0.5% ~ 3.0% IoU on the Cityscapes dataset and gains 1.6% ~ 4.1% in boundary Fscores. We also apply this framework on customized backbones and the emerging vision transformer models and show the effectiveness of the SBCB framework.

2.Density-Insensitive Unsupervised Domain Adaption on 3D Object Detection

Authors:Qianjiang Hu, Daizong Liu, Wei Hu

Abstract: 3D object detection from point clouds is crucial in safety-critical autonomous driving. Although many works have made great efforts and achieved significant progress on this task, most of them suffer from expensive annotation cost and poor transferability to unknown data due to the domain gap. Recently, few works attempt to tackle the domain gap in objects, but still fail to adapt to the gap of varying beam-densities between two domains, which is critical to mitigate the characteristic differences of the LiDAR collectors. To this end, we make the attempt to propose a density-insensitive domain adaption framework to address the density-induced domain gap. In particular, we first introduce Random Beam Re-Sampling (RBRS) to enhance the robustness of 3D detectors trained on the source domain to the varying beam-density. Then, we take this pre-trained detector as the backbone model, and feed the unlabeled target domain data into our newly designed task-specific teacher-student framework for predicting its high-quality pseudo labels. To further adapt the property of density-insensitivity into the target domain, we feed the teacher and student branches with the same sample of different densities, and propose an Object Graph Alignment (OGA) module to construct two object-graphs between the two branches for enforcing the consistency in both the attribute and relation of cross-density objects. Experimental results on three widely adopted 3D object detection datasets demonstrate that our proposed domain adaption method outperforms the state-of-the-art methods, especially over varying-density data. Code is available at https://github.com/WoodwindHu/DTS}{https://github.com/WoodwindHu/DTS.

3.Network Pruning Spaces

Authors:Xuanyu He, Yu-I Yang, Ran Song, Jiachen Pu, Conggang Hu, Feijun Jiang, Wei Zhang, Huanghao Ding

Abstract: Network pruning techniques, including weight pruning and filter pruning, reveal that most state-of-the-art neural networks can be accelerated without a significant performance drop. This work focuses on filter pruning which enables accelerated inference with any off-the-shelf deep learning library and hardware. We propose the concept of \emph{network pruning spaces} that parametrize populations of subnetwork architectures. Based on this concept, we explore the structure aspect of subnetworks that result in minimal loss of accuracy in different pruning regimes and arrive at a series of observations by comparing subnetwork distributions. We conjecture through empirical studies that there exists an optimal FLOPs-to-parameter-bucket ratio related to the design of original network in a pruning regime. Statistically, the structure of a winning subnetwork guarantees an approximately optimal ratio in this regime. Upon our conjectures, we further refine the initial pruning space to reduce the cost of searching a good subnetwork architecture. Our experimental results on ImageNet show that the subnetwork we found is superior to those from the state-of-the-art pruning methods under comparable FLOPs.

4.HyperStyle3D: Text-Guided 3D Portrait Stylization via Hypernetworks

Authors:Zhuo Chen, Xudong Xu, Yichao Yan, Ye Pan, Wenhan Zhu, Wayne Wu, Bo Dai, Xiaokang Yang

Abstract: Portrait stylization is a long-standing task enabling extensive applications. Although 2D-based methods have made great progress in recent years, real-world applications such as metaverse and games often demand 3D content. On the other hand, the requirement of 3D data, which is costly to acquire, significantly impedes the development of 3D portrait stylization methods. In this paper, inspired by the success of 3D-aware GANs that bridge 2D and 3D domains with 3D fields as the intermediate representation for rendering 2D images, we propose a novel method, dubbed HyperStyle3D, based on 3D-aware GANs for 3D portrait stylization. At the core of our method is a hyper-network learned to manipulate the parameters of the generator in a single forward pass. It not only offers a strong capacity to handle multiple styles with a single model, but also enables flexible fine-grained stylization that affects only texture, shape, or local part of the portrait. While the use of 3D-aware GANs bypasses the requirement of 3D data, we further alleviate the necessity of style images with the CLIP model being the stylization guidance. We conduct an extensive set of experiments across the style, attribute, and shape, and meanwhile, measure the 3D consistency. These experiments demonstrate the superior capability of our HyperStyle3D model in rendering 3D-consistent images in diverse styles, deforming the face shape, and editing various attributes.

5.Baybayin Character Instance Detection

Authors:Adriel Isaiah V. Amoguis, Gian Joseph B. Madrid, Benito Miguel D. Flores IV, Macario O. Cordel II

Abstract: The Philippine Government recently passed the "National Writing System Act," which promotes using Baybayin in Philippine texts. In support of this effort to promote the use of Baybayin, we present a computer vision system which can aid individuals who cannot easily read Baybayin script. In this paper, we survey the existing methods of identifying Baybayin scripts using computer vision and machine learning techniques and discuss their capabilities and limitations. Further, we propose a Baybayin Optical Character Instance Segmentation and Classification model using state-of-the-art Convolutional Neural Networks (CNNs) that detect Baybayin character instances in an image then outputs the Latin alphabet counterparts of each character instance in the image. Most existing systems are limited to character-level image classification and often misclassify or not natively support characters with diacritics. In addition, these existing models often have specific input requirements that limit it to classifying Baybayin text in a controlled setting, such as limitations in clarity and contrast, among others. To our knowledge, our proposed method is the first end-to-end character instance detection model for Baybayin, achieving a mAP50 score of 93.30%, mAP50-95 score of 80.50%, and F1-Score of 84.84%.

6.Enhancing Multi-Camera People Tracking with Anchor-Guided Clustering and Spatio-Temporal Consistency ID Re-Assignment

Authors:Hsiang-Wei Huang, Cheng-Yen Yang, Zhongyu Jiang, Pyong-Kun Kim, Kyoungoh Lee, Kwangju Kim, Samartha Ramkumar, Chaitanya Mullapudi, In-Su Jang, Chung-I Huang, Jenq-Neng Hwang

Abstract: Multi-camera multiple people tracking has become an increasingly important area of research due to the growing demand for accurate and efficient indoor people tracking systems, particularly in settings such as retail, healthcare centers, and transit hubs. We proposed a novel multi-camera multiple people tracking method that uses anchor-guided clustering for cross-camera re-identification and spatio-temporal consistency for geometry-based cross-camera ID reassigning. Our approach aims to improve the accuracy of tracking by identifying key features that are unique to every individual and utilizing the overlap of views between cameras to predict accurate trajectories without needing the actual camera parameters. The method has demonstrated robustness and effectiveness in handling both synthetic and real-world data. The proposed method is evaluated on CVPR AI City Challenge 2023 dataset, achieving IDF1 of 95.36% with the first-place ranking in the challenge. The code is available at: https://github.com/ipl-uw/AIC23_Track1_UWIPL_ETRI.

7.DiFaReli : Diffusion Face Relighting

Authors:Puntawat Ponglertnapakorn, Nontawat Tritrong, Supasorn Suwajanakorn

Abstract: We present a novel approach to single-view face relighting in the wild. Handling non-diffuse effects, such as global illumination or cast shadows, has long been a challenge in face relighting. Prior work often assumes Lambertian surfaces, simplified lighting models or involves estimating 3D shape, albedo, or a shadow map. This estimation, however, is error-prone and requires many training examples with lighting ground truth to generalize well. Our work bypasses the need for accurate estimation of intrinsic components and can be trained solely on 2D images without any light stage data, multi-view images, or lighting ground truth. Our key idea is to leverage a conditional diffusion implicit model (DDIM) for decoding a disentangled light encoding along with other encodings related to 3D shape and facial identity inferred from off-the-shelf estimators. We also propose a novel conditioning technique that eases the modeling of the complex interaction between light and geometry by using a rendered shading reference to spatially modulate the DDIM. We achieve state-of-the-art performance on standard benchmark Multi-PIE and can photorealistically relight in-the-wild images. Please visit our page: https://diffusion-face-relighting.github.io

8.Learning Robust Visual-Semantic Embedding for Generalizable Person Re-identification

Authors:Suncheng Xiang, Jingsheng Gao, Mengyuan Guan, Jiacheng Ruan, Chengfeng Zhou, Ting Liu, Dahong Qian, Yuzhuo Fu

Abstract: Generalizable person re-identification (Re-ID) is a very hot research topic in machine learning and computer vision, which plays a significant role in realistic scenarios due to its various applications in public security and video surveillance. However, previous methods mainly focus on the visual representation learning, while neglect to explore the potential of semantic features during training, which easily leads to poor generalization capability when adapted to the new domain. In this paper, we propose a Multi-Modal Equivalent Transformer called MMET for more robust visual-semantic embedding learning on visual, textual and visual-textual tasks respectively. To further enhance the robust feature learning in the context of transformer, a dynamic masking mechanism called Masked Multimodal Modeling strategy (MMM) is introduced to mask both the image patches and the text tokens, which can jointly works on multimodal or unimodal data and significantly boost the performance of generalizable person Re-ID. Extensive experiments on benchmark datasets demonstrate the competitive performance of our method over previous approaches. We hope this method could advance the research towards visual-semantic representation learning. Our source code is also publicly available at https://github.com/JeremyXSC/MMET.

9.Sampling is Matter: Point-guided 3D Human Mesh Reconstruction

Authors:Jeonghwan Kim Konkuk University, Mi-Gyeong Gwon Konkuk University, Hyunwoo Park Konkuk University, Hyukmin Kwon Electronics and Telecommunications Research Institute, Gi-Mun Um Electronics and Telecommunications Research Institute, Wonjun Kim Konkuk University

Abstract: This paper presents a simple yet powerful method for 3D human mesh reconstruction from a single RGB image. Most recently, the non-local interactions of the whole mesh vertices have been effectively estimated in the transformer while the relationship between body parts also has begun to be handled via the graph model. Even though those approaches have shown the remarkable progress in 3D human mesh reconstruction, it is still difficult to directly infer the relationship between features, which are encoded from the 2D input image, and 3D coordinates of each vertex. To resolve this problem, we propose to design a simple feature sampling scheme. The key idea is to sample features in the embedded space by following the guide of points, which are estimated as projection results of 3D mesh vertices (i.e., ground truth). This helps the model to concentrate more on vertex-relevant features in the 2D space, thus leading to the reconstruction of the natural human pose. Furthermore, we apply progressive attention masking to precisely estimate local interactions between vertices even under severe occlusions. Experimental results on benchmark datasets show that the proposed method efficiently improves the performance of 3D human mesh reconstruction. The code and model are publicly available at: https://github.com/DCVL-3D/PointHMR_release.

10.Single-View View Synthesis with Self-Rectified Pseudo-Stereo

Authors:Zhou Yang, Wu Hanjie, Liu Wenxi, Xiong Zheng, Qin Jing, He Shengfeng

Abstract: Synthesizing novel views from a single view image is a highly ill-posed problem. We discover an effective solution to reduce the learning ambiguity by expanding the single-view view synthesis problem to a multi-view setting. Specifically, we leverage the reliable and explicit stereo prior to generate a pseudo-stereo viewpoint, which serves as an auxiliary input to construct the 3D space. In this way, the challenging novel view synthesis process is decoupled into two simpler problems of stereo synthesis and 3D reconstruction. In order to synthesize a structurally correct and detail-preserved stereo image, we propose a self-rectified stereo synthesis to amend erroneous regions in an identify-rectify manner. Hard-to-train and incorrect warping samples are first discovered by two strategies, 1) pruning the network to reveal low-confident predictions; and 2) bidirectionally matching between stereo images to allow the discovery of improper mapping. These regions are then inpainted to form the final pseudo-stereo. With the aid of this extra input, a preferable 3D reconstruction can be easily obtained, and our method can work with arbitrary 3D representations. Extensive experiments show that our method outperforms state-of-the-art single-view view synthesis methods and stereo synthesis methods.

11.Realistic Data Enrichment for Robust Image Segmentation in Histopathology

Authors:Sarah Cechnicka, James Ball, Callum Arthurs, Candice Roufosse, Bernhard Kainz

Abstract: Poor performance of quantitative analysis in histopathological Whole Slide Images (WSI) has been a significant obstacle in clinical practice. Annotating large-scale WSIs manually is a demanding and time-consuming task, unlikely to yield the expected results when used for fully supervised learning systems. Rarely observed disease patterns and large differences in object scales are difficult to model through conventional patient intake. Prior methods either fall back to direct disease classification, which only requires learning a few factors per image, or report on average image segmentation performance, which is highly biased towards majority observations. Geometric image augmentation is commonly used to improve robustness for average case predictions and to enrich limited datasets. So far no method provided sampling of a realistic posterior distribution to improve stability, e.g. for the segmentation of imbalanced objects within images. Therefore, we propose a new approach, based on diffusion models, which can enrich an imbalanced dataset with plausible examples from underrepresented groups by conditioning on segmentation maps. Our method can simply expand limited clinical datasets making them suitable to train machine learning pipelines, and provides an interpretable and human-controllable way of generating histopathology images that are indistinguishable from real ones to human experts. We validate our findings on two datasets, one from the public domain and one from a Kidney Transplant study.

12.SLIC: Self-Conditioned Adaptive Transform with Large-Scale Receptive Fields for Learned Image Compression

Authors:Wei Jiang, Peirong Ning, Ronggang Wang

Abstract: Learned image compression has achieved remarkable performance. Transform, plays an important role in boosting the RD performance. Analysis transform converts the input image to a compact latent representation. The more compact the latent representation is, the fewer bits we need to compress it. When designing better transform, some previous works adopt Swin-Transformer. The success of the Swin-Transformer in image compression can be attributed to the dynamic weights and large receptive field.However,the LayerNorm adopted in transformers is not suitable for image compression.We find CNN-based modules can also be dynamic and have large receptive-fields. The CNN-based modules can also work with GDN/IGDN. To make the CNN-based modules dynamic, we generate the weights of kernels conditioned on the input feature. We scale up the size of each kernel for larger receptive fields. To reduce complexity, we make the CNN-module channel-wise connected. We call this module Dynamic Depth-wise convolution. We replace the self-attention module with the proposed Dynamic Depth-wise convolution, replace the embedding layer with a depth-wise residual bottleneck for non-linearity and replace the FFN layer with an inverted residual bottleneck for more interactions in the spatial domain. The interactions among channels of dynamic depth-wise convolution are limited. We design the other block, which replaces the dynamic depth-wise convolution with channel attention. We equip the proposed modules in the analysis and synthesis transform and receive a more compact latent representation and propose the learned image compression model SLIC, meaning Self-Conditioned Adaptive Transform with Large-Scale Receptive Fields for Learned Image Compression Learned Image Compression. Thanks to the proposed transform modules, our proposed SLIC achieves 6.35% BD-rate reduction over VVC when measured in PSNR on Kodak dataset.

13.DADFNet: Dual Attention and Dual Frequency-Guided Dehazing Network for Video-Empowered Intelligent Transportation

Authors:Yu Guo, Ryan Wen Liu, Jiangtian Nie, Lingjuan Lyu, Zehui Xiong, Jiawen Kang, Han Yu, Dusit Niyato

Abstract: Visual surveillance technology is an indispensable functional component of advanced traffic management systems. It has been applied to perform traffic supervision tasks, such as object detection, tracking and recognition. However, adverse weather conditions, e.g., fog, haze and mist, pose severe challenges for video-based transportation surveillance. To eliminate the influences of adverse weather conditions, we propose a dual attention and dual frequency-guided dehazing network (termed DADFNet) for real-time visibility enhancement. It consists of a dual attention module (DAM) and a high-low frequency-guided sub-net (HLFN) to jointly consider the attention and frequency mapping to guide haze-free scene reconstruction. Extensive experiments on both synthetic and real-world images demonstrate the superiority of DADFNet over state-of-the-art methods in terms of visibility enhancement and improvement in detection accuracy. Furthermore, DADFNet only takes $6.3$ ms to process a 1,920 * 1,080 image on the 2080 Ti GPU, making it highly efficient for deployment in intelligent transportation systems.

14.MMDR: A Result Feature Fusion Object Detection Approach for Autonomous System

Authors:Wendong Zhang

Abstract: Object detection has been extensively utilized in autonomous systems in recent years, encompassing both 2D and 3D object detection. Recent research in this field has primarily centered around multimodal approaches for addressing this issue.In this paper, a multimodal fusion approach based on result feature-level fusion is proposed. This method utilizes the outcome features generated from single modality sources, and fuses them for downstream tasks.Based on this method, a new post-fusing network is proposed for multimodal object detection, which leverages the single modality outcomes as features. The proposed approach, called Multi-Modal Detector based on Result features (MMDR), is designed to work for both 2D and 3D object detection tasks. Compared to previous multimodal models, the proposed approach in this paper performs feature fusion at a later stage, enabling better representation of the deep-level features of single modality sources. Additionally, the MMDR model incorporates shallow global features during the feature fusion stage, endowing the model with the ability to perceive background information and the overall input, thereby avoiding issues such as missed detections.

15.CHATTY: Coupled Holistic Adversarial Transport Terms with Yield for Unsupervised Domain Adaptation

Authors:Chirag P, Mukta Wagle, Ravi Kant Gupta, Pranav Jeevan P, Amit Sethi

Abstract: We propose a new technique called CHATTY: Coupled Holistic Adversarial Transport Terms with Yield for Unsupervised Domain Adaptation. Adversarial training is commonly used for learning domain-invariant representations by reversing the gradients from a domain discriminator head to train the feature extractor layers of a neural network. We propose significant modifications to the adversarial head, its training objective, and the classifier head. With the aim of reducing class confusion, we introduce a sub-network which displaces the classifier outputs of the source and target domain samples in a learnable manner. We control this movement using a novel transport loss that spreads class clusters away from each other and makes it easier for the classifier to find the decision boundaries for both the source and target domains. The results of adding this new loss to a careful selection of previously proposed losses leads to improvement in UDA results compared to the previous state-of-the-art methods on benchmark datasets. We show the importance of the proposed loss term using ablation studies and visualization of the movement of target domain sample in representation space.

16.Automatic Individual Identification of Patterned Solitary Species Based on Unlabeled Video Data

Authors:Vanessa Suessle, Mimi Arandjelovic, Ammie K. Kalan, Anthony Agbor, Christophe Boesch, Gregory Brazzola, Tobias Deschner, Paula Dieguez, Anne-Céline Granjon, Hjalmar Kuehl, Anja Landsmann, Juan Lapuente, Nuria Maldonado, Amelia Meier, Zuzana Rockaiova, Erin G. Wessling, Roman M. Wittig, Colleen T. Downs, Andreas Weinmann, Elke Hergenroether

Abstract: The manual processing and analysis of videos from camera traps is time-consuming and includes several steps, ranging from the filtering of falsely triggered footage to identifying and re-identifying individuals. In this study, we developed a pipeline to automatically analyze videos from camera traps to identify individuals without requiring manual interaction. This pipeline applies to animal species with uniquely identifiable fur patterns and solitary behavior, such as leopards (Panthera pardus). We assumed that the same individual was seen throughout one triggered video sequence. With this assumption, multiple images could be assigned to an individual for the initial database filling without pre-labeling. The pipeline was based on well-established components from computer vision and deep learning, particularly convolutional neural networks (CNNs) and scale-invariant feature transform (SIFT) features. We augmented this basis by implementing additional components to substitute otherwise required human interactions. Based on the similarity between frames from the video material, clusters were formed that represented individuals bypassing the open set problem of the unknown total population. The pipeline was tested on a dataset of leopard videos collected by the Pan African Programme: The Cultured Chimpanzee (PanAf) and achieved a success rate of over 83% for correct matches between previously unknown individuals. The proposed pipeline can become a valuable tool for future conservation projects based on camera trap data, reducing the work of manual analysis for individual identification, when labeled data is unavailable.

17.CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understanding

Authors:Dilxat Muhtar, Xueliang Zhang, Pengfeng Xiao, Zhenshi Li, Feng Gu

Abstract: Self-supervised learning (SSL) has gained widespread attention in the remote sensing (RS) and earth observation (EO) communities owing to its ability to learn task-agnostic representations without human-annotated labels. Nevertheless, most existing RS SSL methods are limited to learning either global semantic separable or local spatial perceptible representations. We argue that this learning strategy is suboptimal in the realm of RS, since the required representations for different RS downstream tasks are often varied and complex. In this study, we proposed a unified SSL framework that is better suited for RS images representation learning. The proposed SSL framework, Contrastive Mask Image Distillation (CMID), is capable of learning representations with both global semantic separability and local spatial perceptibility by combining contrastive learning (CL) with masked image modeling (MIM) in a self-distillation way. Furthermore, our CMID learning framework is architecture-agnostic, which is compatible with both convolutional neural networks (CNN) and vision transformers (ViT), allowing CMID to be easily adapted to a variety of deep learning (DL) applications for RS understanding. Comprehensive experiments have been carried out on four downstream tasks (i.e. scene classification, semantic segmentation, object-detection, and change detection) and the results show that models pre-trained using CMID achieve better performance than other state-of-the-art SSL methods on multiple downstream tasks. The code and pre-trained models will be made available at https://github.com/NJU-LHRS/official-CMID to facilitate SSL research and speed up the development of RS images DL applications.

18.Reference-guided Controllable Inpainting of Neural Radiance Fields

Authors:Ashkan Mirzaei, Tristan Aumentado-Armstrong, Marcus A. Brubaker, Jonathan Kelly, Alex Levinshtein, Konstantinos G. Derpanis, Igor Gilitschenski

Abstract: The popularity of Neural Radiance Fields (NeRFs) for view synthesis has led to a desire for NeRF editing tools. Here, we focus on inpainting regions in a view-consistent and controllable manner. In addition to the typical NeRF inputs and masks delineating the unwanted region in each view, we require only a single inpainted view of the scene, i.e., a reference view. We use monocular depth estimators to back-project the inpainted view to the correct 3D positions. Then, via a novel rendering technique, a bilateral solver can construct view-dependent effects in non-reference views, making the inpainted region appear consistent from any view. For non-reference disoccluded regions, which cannot be supervised by the single reference view, we devise a method based on image inpainters to guide both the geometry and appearance. Our approach shows superior performance to NeRF inpainting baselines, with the additional advantage that a user can control the generated scene via a single inpainted image. Project page: https://ashmrz.github.io/reference-guided-3d

19.DarSwin: Distortion Aware Radial Swin Transformer

Authors:Akshaya Athwale, Arman Afrasiyabi, Justin Lague, Ichrak Shili, Ola Ahmad, Jean-Francois Lalonde

Abstract: Wide-angle lenses are commonly used in perception tasks requiring a large field of view. Unfortunately, these lenses produce significant distortions making conventional models that ignore the distortion effects unable to adapt to wide-angle images. In this paper, we present a novel transformer-based model that automatically adapts to the distortion produced by wide-angle lenses. We leverage the physical characteristics of such lenses, which are analytically defined by the radial distortion profile (assumed to be known), to develop a distortion aware radial swin transformer (DarSwin). In contrast to conventional transformer-based architectures, DarSwin comprises a radial patch partitioning, a distortion-based sampling technique for creating token embeddings, and a polar position encoding for radial patch merging. We validate our method on classification tasks using synthetically distorted ImageNet data and show through extensive experiments that DarSwin can perform zero-shot adaptation to unseen distortions of different wide-angle lenses. Compared to other baselines, DarSwin achieves the best results (in terms of Top-1 and -5 accuracy), when tested on in-distribution data, with almost 2% (6%) gain in Top-1 accuracy under medium (high) distortion levels, and comparable to the state-of-the-art under low and very low distortion levels (perspective-like images).

20.CrossFusion: Interleaving Cross-modal Complementation for Noise-resistant 3D Object Detection

Authors:Yang Yang, Weijie Ma, Hao Chen, Linlin Ou, Xinyi Yu

Abstract: The combination of LiDAR and camera modalities is proven to be necessary and typical for 3D object detection according to recent studies. Existing fusion strategies tend to overly rely on the LiDAR modal in essence, which exploits the abundant semantics from the camera sensor insufficiently. However, existing methods cannot rely on information from other modalities because the corruption of LiDAR features results in a large domain gap. Following this, we propose CrossFusion, a more robust and noise-resistant scheme that makes full use of the camera and LiDAR features with the designed cross-modal complementation strategy. Extensive experiments we conducted show that our method not only outperforms the state-of-the-art methods under the setting without introducing an extra depth estimation network but also demonstrates our model's noise resistance without re-training for the specific malfunction scenarios by increasing 5.2\% mAP and 2.4\% NDS.

21.Learnable Earth Parser: Discovering 3D Prototypes in Aerial Scans

Authors:Romain Loiseau, Elliot Vincent, Mathieu Aubry, Loic Landrieu

Abstract: We propose an unsupervised method for parsing large 3D scans of real-world scenes into interpretable parts. Our goal is to provide a practical tool for analyzing 3D scenes with unique characteristics in the context of aerial surveying and mapping, without relying on application-specific user annotations. Our approach is based on a probabilistic reconstruction model that decomposes an input 3D point cloud into a small set of learned prototypical shapes. Our model provides an interpretable reconstruction of complex scenes and leads to relevant instance and semantic segmentations. To demonstrate the usefulness of our results, we introduce a novel dataset of seven diverse aerial LiDAR scans. We show that our method outperforms state-of-the-art unsupervised methods in terms of decomposition accuracy while remaining visually interpretable. Our method offers significant advantage over existing approaches, as it does not require any manual annotations, making it a practical and efficient tool for 3D scene analysis. Our code and dataset are available at https://imagine.enpc.fr/~loiseaur/learnable-earth-parser

22.Disentangling Neuron Representations with Concept Vectors

Authors:Laura O'Mahony, Vincent Andrearczyk, Henning Muller, Mara Graziani

Abstract: Mechanistic interpretability aims to understand how models store representations by breaking down neural networks into interpretable units. However, the occurrence of polysemantic neurons, or neurons that respond to multiple unrelated features, makes interpreting individual neurons challenging. This has led to the search for meaningful vectors, known as concept vectors, in activation space instead of individual neurons. The main contribution of this paper is a method to disentangle polysemantic neurons into concept vectors encapsulating distinct features. Our method can search for fine-grained concepts according to the user's desired level of concept separation. The analysis shows that polysemantic neurons can be disentangled into directions consisting of linear combinations of neurons. Our evaluations show that the concept vectors found encode coherent, human-understandable features.

23.UniCal: a Single-Branch Transformer-Based Model for Camera-to-LiDAR Calibration and Validation

Authors:Mathieu Cocheteux, Aaron Low, Marius Bruehlmeier

Abstract: We introduce a novel architecture, UniCal, for Camera-to-LiDAR (C2L) extrinsic calibration which leverages self-attention mechanisms through a Transformer-based backbone network to infer the 6-degree of freedom (DoF) relative transformation between the sensors. Unlike previous methods, UniCal performs an early fusion of the input camera and LiDAR data by aggregating camera image channels and LiDAR mappings into a multi-channel unified representation before extracting their features jointly with a single-branch architecture. This single-branch architecture makes UniCal lightweight, which is desirable in applications with restrained resources such as autonomous driving. Through experiments, we show that UniCal achieves state-of-the-art results compared to existing methods. We also show that through transfer learning, weights learned on the calibration task can be applied to a calibration validation task without re-training the backbone.

24.Improved Active Fire Detection using Operational U-Nets

Authors:Ozer Can Devecioglu, Mete Ahishali, Fahad Sohrab, Turker Ince, Moncef Gabbouj

Abstract: As a consequence of global warming and climate change, the risk and extent of wildfires have been increasing in many areas worldwide. Warmer temperatures and drier conditions can cause quickly spreading fires and make them harder to control; therefore, early detection and accurate locating of active fires are crucial in environmental monitoring. Using satellite imagery to monitor and detect active fires has been critical for managing forests and public land. Many traditional statistical-based methods and more recent deep-learning techniques have been proposed for active fire detection. In this study, we propose a novel approach called Operational U-Nets for the improved early detection of active fires. The proposed approach utilizes Self-Organized Operational Neural Network (Self-ONN) layers in a compact U-Net architecture. The preliminary experimental results demonstrate that Operational U-Nets not only achieve superior detection performance but can also significantly reduce computational complexity.

25.Any-to-Any Style Transfer

Authors:Songhua Liu, Jingwen Ye, Xinchao Wang

Abstract: Style transfer aims to render the style of a given image for style reference to another given image for content reference, and has been widely adopted in artistic generation and image editing. Existing approaches either apply the holistic style of the style image in a global manner, or migrate local colors and textures of the style image to the content counterparts in a pre-defined way. In either case, only one result can be generated for a specific pair of content and style images, which therefore lacks flexibility and is hard to satisfy different users with different preferences. We propose here a novel strategy termed Any-to-Any Style Transfer to address this drawback, which enables users to interactively select styles of regions in the style image and apply them to the prescribed content regions. In this way, personalizable style transfer is achieved through human-computer interaction. At the heart of our approach lies in (1) a region segmentation module based on Segment Anything, which supports region selection with only some clicks or drawing on images and thus takes user inputs conveniently and flexibly; (2) and an attention fusion module, which converts inputs from users to controlling signals for the style transfer model. Experiments demonstrate their effectiveness for personalizable style transfer. Notably, our approach performs in a plug-and-play manner portable to any style transfer method and enhance the controllablity. Our code is available \href{https://github.com/Huage001/Transfer-Any-Style}{here}.

26.Hyperspectral Image Analysis with Subspace Learning-based One-Class Classification

Authors:Sertac Kilickaya, Mete Ahishali, Fahad Sohrab, Turker Ince, Moncef Gabbouj

Abstract: Hyperspectral image (HSI) classification is an important task in many applications, such as environmental monitoring, medical imaging, and land use/land cover (LULC) classification. Due to the significant amount of spectral information from recent HSI sensors, analyzing the acquired images is challenging using traditional Machine Learning (ML) methods. As the number of frequency bands increases, the required number of training samples increases exponentially to achieve a reasonable classification accuracy, also known as the curse of dimensionality. Therefore, separate band selection or dimensionality reduction techniques are often applied before performing any classification task over HSI data. In this study, we investigate recently proposed subspace learning methods for one-class classification (OCC). These methods map high-dimensional data to a lower-dimensional feature space that is optimized for one-class classification. In this way, there is no separate dimensionality reduction or feature selection procedure needed in the proposed classification framework. Moreover, one-class classifiers have the ability to learn a data description from the category of a single class only. Considering the imbalanced labels of the LULC classification problem and rich spectral information (high number of dimensions), the proposed classification approach is well-suited for HSI data. Overall, this is a pioneer study focusing on subspace learning-based one-class classification for HSI data. We analyze the performance of the proposed subspace learning one-class classifiers in the proposed pipeline. Our experiments validate that the proposed approach helps tackle the curse of dimensionality along with the imbalanced nature of HSI data.

27.Rehabilitation Exercise Repetition Segmentation and Counting using Skeletal Body Joints

Authors:Ali Abedi, Paritosh Bisht, Riddhi Chatterjee, Rachit Agrawal, Vyom Sharma, Dinesh Babu Jayagopi, Shehroz S. Khan

Abstract: Physical exercise is an essential component of rehabilitation programs that improve quality of life and reduce mortality and re-hospitalization rates. In AI-driven virtual rehabilitation programs, patients complete their exercises independently at home, while AI algorithms analyze the exercise data to provide feedback to patients and report their progress to clinicians. To analyze exercise data, the first step is to segment it into consecutive repetitions. There has been a significant amount of research performed on segmenting and counting the repetitive activities of healthy individuals using raw video data, which raises concerns regarding privacy and is computationally intensive. Previous research on patients' rehabilitation exercise segmentation relied on data collected by multiple wearable sensors, which are difficult to use at home by rehabilitation patients. Compared to healthy individuals, segmenting and counting exercise repetitions in patients is more challenging because of the irregular repetition duration and the variation between repetitions. This paper presents a novel approach for segmenting and counting the repetitions of rehabilitation exercises performed by patients, based on their skeletal body joints. Skeletal body joints can be acquired through depth cameras or computer vision techniques applied to RGB videos of patients. Various sequential neural networks are designed to analyze the sequences of skeletal body joints and perform repetition segmentation and counting. Extensive experiments on three publicly available rehabilitation exercise datasets, KIMORE, UI-PRMD, and IntelliRehabDS, demonstrate the superiority of the proposed method compared to previous methods. The proposed method enables accurate exercise analysis while preserving privacy, facilitating the effective delivery of virtual rehabilitation programs.

28.An End-to-End Vehicle Trajcetory Prediction Framework

Authors:Fuad Hasan, Hailong Huang

Abstract: Anticipating the motion of neighboring vehicles is crucial for autonomous driving, especially on congested highways where even slight motion variations can result in catastrophic collisions. An accurate prediction of a future trajectory does not just rely on the previous trajectory, but also, more importantly, a simulation of the complex interactions between other vehicles nearby. Most state-of-the-art networks built to tackle the problem assume readily available past trajectory points, hence lacking a full end-to-end pipeline with direct video-to-output mechanism. In this article, we thus propose a novel end-to-end architecture that takes raw video inputs and outputs future trajectory predictions. It first extracts and tracks the 3D location of the nearby vehicles via multi-head attention-based regression networks as well as non-linear optimization. This provides the past trajectory points which then feeds into the trajectory prediction algorithm consisting of an attention-based LSTM encoder-decoder architecture, which allows it to model the complicated interdependence between the vehicles and make an accurate prediction of the future trajectory points of the surrounding vehicles. The proposed model is evaluated on the large-scale BLVD dataset, and has also been implemented on CARLA. The experimental results demonstrate that our approach outperforms various state-of-the-art models.

29.Post-Training Quantization for Object Detection

Authors:Lin Niu, Jiawei Liu, Zhihang Yuan, Dawei Yang, Xinggang Wang, Wenyu Liu

Abstract: Efficient inference for object detection networks is a major challenge on edge devices. Post-Training Quantization (PTQ), which transforms a full-precision model into low bit-width directly, is an effective and convenient approach to reduce model inference complexity. But it suffers severe accuracy drop when applied to complex tasks such as object detection. PTQ optimizes the quantization parameters by different metrics to minimize the perturbation of quantization. The p-norm distance of feature maps before and after quantization, Lp, is widely used as the metric to evaluate perturbation. For the specialty of object detection network, we observe that the parameter p in Lp metric will significantly influence its quantization performance. We indicate that using a fixed hyper-parameter p does not achieve optimal quantization performance. To mitigate this problem, we propose a framework, DetPTQ, to assign different p values for quantizing different layers using an Object Detection Output Loss (ODOL), which represents the task loss of object detection. DetPTQ employs the ODOL-based adaptive Lp metric to select the optimal quantization parameters. Experiments show that our DetPTQ outperforms the state-of-the-art PTQ methods by a significant margin on both 2D and 3D object detectors. For example, we achieve 31.1/31.7(quantization/full-precision) mAP on RetinaNet-ResNet18 with 4-bit weight and 4-bit activation.

30.NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Models

Authors:Seung Wook Kim, Bradley Brown, Kangxue Yin, Karsten Kreis, Katja Schwarz, Daiqing Li, Robin Rombach, Antonio Torralba, Sanja Fidler

Abstract: Automatically generating high-quality real world 3D scenes is of enormous interest for applications such as virtual reality and robotics simulation. Towards this goal, we introduce NeuralField-LDM, a generative model capable of synthesizing complex 3D environments. We leverage Latent Diffusion Models that have been successfully utilized for efficient high-quality 2D content creation. We first train a scene auto-encoder to express a set of image and pose pairs as a neural field, represented as density and feature voxel grids that can be projected to produce novel views of the scene. To further compress this representation, we train a latent-autoencoder that maps the voxel grids to a set of latent representations. A hierarchical diffusion model is then fit to the latents to complete the scene generation pipeline. We achieve a substantial improvement over existing state-of-the-art scene generation models. Additionally, we show how NeuralField-LDM can be used for a variety of 3D content creation applications, including conditional scene generation, scene inpainting and scene style manipulation.

31.Automatic Interaction and Activity Recognition from Videos of Human Manual Demonstrations with Application to Anomaly Detection

Authors:Elena Merlo Human-Robot Interfaces and Interaction Laboratory, Istituto Italiano di Tecnologia, Genoa, Italy Dept. of Informatics, Bioengineering, Robotics, and Systems Engineering, University of Genoa, Genoa, Italy, Marta Lagomarsino Human-Robot Interfaces and Interaction Laboratory, Istituto Italiano di Tecnologia, Genoa, Italy Dept. of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy, Edoardo Lamon Human-Robot Interfaces and Interaction Laboratory, Istituto Italiano di Tecnologia, Genoa, Italy, Arash Ajoudani Human-Robot Interfaces and Interaction Laboratory, Istituto Italiano di Tecnologia, Genoa, Italy

Abstract: This paper presents a new method to describe spatio-temporal relations between objects and hands, to recognize both interactions and activities within video demonstrations of manual tasks. The approach exploits Scene Graphs to extract key interaction features from image sequences, encoding at the same time motion patterns and context. Additionally, the method introduces an event-based automatic video segmentation and clustering, which allows to group similar events, detecting also on the fly if a monitored activity is executed correctly. The effectiveness of the approach was demonstrated in two multi-subject experiments, showing the ability to recognize and cluster hand-object and object-object interactions without prior knowledge of the activity, as well as matching the same activity performed by different subjects.

32.AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation

Authors:Zhen Li, Zuo-Liang Zhu, Ling-Hao Han, Qibin Hou, Chun-Le Guo, Ming-Ming Cheng

Abstract: We present All-Pairs Multi-Field Transforms (AMT), a new network architecture for video frame interpolation. It is based on two essential designs. First, we build bidirectional correlation volumes for all pairs of pixels, and use the predicted bilateral flows to retrieve correlations for updating both flows and the interpolated content feature. Second, we derive multiple groups of fine-grained flow fields from one pair of updated coarse flows for performing backward warping on the input frames separately. Combining these two designs enables us to generate promising task-oriented flows and reduce the difficulties in modeling large motions and handling occluded areas during frame interpolation. These qualities promote our model to achieve state-of-the-art performance on various benchmarks with high efficiency. Moreover, our convolution-based model competes favorably compared to Transformer-based models in terms of accuracy and efficiency. Our code is available at https://github.com/MCG-NKU/AMT.

33.Event-based Simultaneous Localization and Mapping: A Comprehensive Survey

Authors:Kunping Huang, Sen Zhang, Jing Zhang, Dacheng Tao

Abstract: In recent decades, visual simultaneous localization and mapping (vSLAM) has gained significant interest in both academia and industry. It estimates camera motion and reconstructs the environment concurrently using visual sensors on a moving robot. However, conventional cameras are limited by hardware, including motion blur and low dynamic range, which can negatively impact performance in challenging scenarios like high-speed motion and high dynamic range illumination. Recent studies have demonstrated that event cameras, a new type of bio-inspired visual sensor, offer advantages such as high temporal resolution, dynamic range, low power consumption, and low latency. This paper presents a timely and comprehensive review of event-based vSLAM algorithms that exploit the benefits of asynchronous and irregular event streams for localization and mapping tasks. The review covers the working principle of event cameras and various event representations for preprocessing event data. It also categorizes event-based vSLAM methods into four main categories: feature-based, direct, motion-compensation, and deep learning methods, with detailed discussions and practical guidance for each approach. Furthermore, the paper evaluates the state-of-the-art methods on various benchmarks, highlighting current challenges and future opportunities in this emerging research area. A public repository will be maintained to keep track of the rapid developments in this field at {\url{https://github.com/kun150kun/ESLAM-survey}}.

34.MetaBEV: Solving Sensor Failures for BEV Detection and Map Segmentation

Authors:Chongjian Ge, Junsong Chen, Enze Xie, Zhongdao Wang, Lanqing Hong, Huchuan Lu, Zhenguo Li, Ping Luo

Abstract: Perception systems in modern autonomous driving vehicles typically take inputs from complementary multi-modal sensors, e.g., LiDAR and cameras. However, in real-world applications, sensor corruptions and failures lead to inferior performances, thus compromising autonomous safety. In this paper, we propose a robust framework, called MetaBEV, to address extreme real-world environments involving overall six sensor corruptions and two extreme sensor-missing situations. In MetaBEV, signals from multiple sensors are first processed by modal-specific encoders. Subsequently, a set of dense BEV queries are initialized, termed meta-BEV. These queries are then processed iteratively by a BEV-Evolving decoder, which selectively aggregates deep features from either LiDAR, cameras, or both modalities. The updated BEV representations are further leveraged for multiple 3D prediction tasks. Additionally, we introduce a new M2oE structure to alleviate the performance drop on distinct tasks in multi-task joint learning. Finally, MetaBEV is evaluated on the nuScenes dataset with 3D object detection and BEV map segmentation tasks. Experiments show MetaBEV outperforms prior arts by a large margin on both full and corrupted modalities. For instance, when the LiDAR signal is missing, MetaBEV improves 35.5% detection NDS and 17.7% segmentation mIoU upon the vanilla BEVFusion model; and when the camera signal is absent, MetaBEV still achieves 69.2% NDS and 53.7% mIoU, which is even higher than previous works that perform on full-modalities. Moreover, MetaBEV performs fairly against previous methods in both canonical perception and multi-task learning settings, refreshing state-of-the-art nuScenes BEV map segmentation with 70.4% mIoU.

35.VMA: Divide-and-Conquer Vectorized Map Annotation System for Large-Scale Driving Scene

Authors:Shaoyu Chen, Yunchi Zhang, Bencheng Liao, Jiafeng Xie, Tianheng Cheng, Wei Sui, Qian Zhang, Chang Huang, Wenyu Liu, Xinggang Wang

Abstract: High-definition (HD) map serves as the essential infrastructure of autonomous driving. In this work, we build up a systematic vectorized map annotation framework (termed VMA) for efficiently generating HD map of large-scale driving scene. We design a divide-and-conquer annotation scheme to solve the spatial extensibility problem of HD map generation, and abstract map elements with a variety of geometric patterns as unified point sequence representation, which can be extended to most map elements in the driving scene. VMA is highly efficient and extensible, requiring negligible human effort, and flexible in terms of spatial scale and element type. We quantitatively and qualitatively validate the annotation performance on real-world urban and highway scenes, as well as NYC Planimetric Database. VMA can significantly improve map generation efficiency and require little human effort. On average VMA takes 160min for annotating a scene with a range of hundreds of meters, and reduces 52.3% of the human cost, showing great application value.

36.Transformer-Based Visual Segmentation: A Survey

Authors:Xiangtai Li, Henghui Ding, Wenwei Zhang, Haobo Yuan, Jiangmiao Pang, Guangliang Cheng, Kai Chen, Ziwei Liu, Chen Change Loy

Abstract: Visual segmentation seeks to partition images, video frames, or point clouds into multiple segments or groups. This technique has numerous real-world applications, such as autonomous driving, image editing, robot sensing, and medical analysis. Over the past decade, deep learning-based methods have made remarkable strides in this area. Recently, transformers, a type of neural network based on self-attention originally designed for natural language processing, have considerably surpassed previous convolutional or recurrent approaches in various vision processing tasks. Specifically, vision transformers offer robust, unified, and even simpler solutions for various segmentation tasks. This survey provides a thorough overview of transformer-based visual segmentation, summarizing recent advancements. We first review the background, encompassing problem definitions, datasets, and prior convolutional methods. Next, we summarize a meta-architecture that unifies all recent transformer-based approaches. Based on this meta-architecture, we examine various method designs, including modifications to the meta-architecture and associated applications. We also present several closely related settings, including 3D point cloud segmentation, foundation model tuning, domain-aware segmentation, efficient segmentation, and medical segmentation. Additionally, we compile and re-evaluate the reviewed methods on several well-established datasets. Finally, we identify open challenges in this field and propose directions for future research. The project page can be found at https://github.com/lxtGH/Awesome-Segmenation-With-Transformer. We will also continually monitor developments in this rapidly evolving field.

37.LipsFormer: Introducing Lipschitz Continuity to Vision Transformers

Authors:Xianbiao Qi, Jianan Wang, Yihao Chen, Yukai Shi, Lei Zhang

Abstract: We present a Lipschitz continuous Transformer, called LipsFormer, to pursue training stability both theoretically and empirically for Transformer-based models. In contrast to previous practical tricks that address training instability by learning rate warmup, layer normalization, attention formulation, and weight initialization, we show that Lipschitz continuity is a more essential property to ensure training stability. In LipsFormer, we replace unstable Transformer component modules with Lipschitz continuous counterparts: CenterNorm instead of LayerNorm, spectral initialization instead of Xavier initialization, scaled cosine similarity attention instead of dot-product attention, and weighted residual shortcut. We prove that these introduced modules are Lipschitz continuous and derive an upper bound on the Lipschitz constant of LipsFormer. Our experiments show that LipsFormer allows stable training of deep Transformer architectures without the need of careful learning rate tuning such as warmup, yielding a faster convergence and better generalization. As a result, on the ImageNet 1K dataset, LipsFormer-Swin-Tiny based on Swin Transformer training for 300 epochs can obtain 82.7\% without any learning rate warmup. Moreover, LipsFormer-CSwin-Tiny, based on CSwin, training for 300 epochs achieves a top-1 accuracy of 83.5\% with 4.7G FLOPs and 24M parameters. The code will be released at \url{https://github.com/IDEA-Research/LipsFormer}.