Computer Vision and Pattern Recognition (cs.CV)

Abstract: Existing text-to-image generation approaches have set high standards for photorealism and text-image correspondence, largely benefiting from web-scale text-image datasets, which can include up to 5~billion pairs. However, text-to-image generation models trained on domain-specific datasets, such as urban scenes, medical images, and faces, still suffer from low text-image correspondence due to the lack of text-image pairs. Additionally, collecting billions of text-image pairs for a specific domain can be time-consuming and costly. Thus, ensuring high text-image correspondence without relying on web-scale text-image datasets remains a challenging task. In this paper, we present a novel approach for enhancing text-image correspondence by leveraging available semantic layouts. Specifically, we propose a Gaussian-categorical diffusion process that simultaneously generates both images and corresponding layout pairs. Our experiments reveal that we can guide text-to-image generation models to be aware of the semantics of different image regions, by training the model to generate semantic labels for each pixel. We demonstrate that our approach achieves higher text-image correspondence compared to existing text-to-image generation approaches in the Multi-Modal CelebA-HQ and the Cityscapes dataset, where text-image pairs are scarce. Codes are available in this https://pmh9960.github.io/research/GCDP

Abstract: Prototypical parts-based networks are becoming increasingly popular due to their faithful self-explanations. However, their similarity maps are calculated in the penultimate network layer. Therefore, the receptive field of the prototype activation region often depends on parts of the image outside this region, which can lead to misleading interpretations. We name this undesired behavior a spatial explanation misalignment and introduce an interpretability benchmark with a set of dedicated metrics for quantifying this phenomenon. In addition, we propose a method for misalignment compensation and apply it to existing state-of-the-art models. We show the expressiveness of our benchmark and the effectiveness of the proposed compensation methodology through extensive empirical studies.

Abstract: Domain adaptive detection aims to improve the generality of a detector, learned from the labeled source domain, on the unlabeled target domain. In this work, drawing inspiration from the concept of stability from the control theory that a robust system requires to remain consistent both externally and internally regardless of disturbances, we propose a novel framework that achieves unsupervised domain adaptive detection through stability analysis. In specific, we treat discrepancies between images and regions from different domains as disturbances, and introduce a novel simple but effective Network Stability Analysis (NSA) framework that considers various disturbances for domain adaptation. Particularly, we explore three types of perturbations including heavy and light image-level disturbances and instancelevel disturbance. For each type, NSA performs external consistency analysis on the outputs from raw and perturbed images and/or internal consistency analysis on their features, using teacher-student models. By integrating NSA into Faster R-CNN, we immediately achieve state-of-the-art results. In particular, we set a new record of 52.7% mAP on Cityscapes-to-FoggyCityscapes, showing the potential of NSA for domain adaptive detection. It is worth noticing, our NSA is designed for general purpose, and thus applicable to one-stage detection model (e.g., FCOS) besides the adopted one, as shown by experiments. https://github.com/tiankongzhang/NSA.

Abstract: Parking guidance information (PGI) systems are used to provide information to drivers about the nearest parking lots and the number of vacant parking slots. Recently, vision-based solutions started to appear as a cost-effective alternative to standard PGI systems based on hardware sensors mounted on each parking slot. Vision-based systems provide information about parking occupancy based on images taken by a camera that is recording a parking lot. However, such systems are challenging to develop due to various possible viewpoints, weather conditions, and object occlusions. Most notably, they require manual labeling of parking slot locations in the input image which is sensitive to camera angle change, replacement, or maintenance. In this paper, the algorithm that performs Automatic Parking Slot Detection and Occupancy Classification (APSD-OC) solely on input images is proposed. Automatic parking slot detection is based on vehicle detections in a series of parking lot images upon which clustering is applied in bird's eye view to detect parking slots. Once the parking slots positions are determined in the input image, each detected parking slot is classified as occupied or vacant using a specifically trained ResNet34 deep classifier. The proposed approach is extensively evaluated on well-known publicly available datasets (PKLot and CNRPark+EXT), showing high efficiency in parking slot detection and robustness to the presence of illegal parking or passing vehicles. Trained classifier achieves high accuracy in parking slot occupancy classification.

Abstract: Physical experiments often involve multiple imaging representations, such as X-ray scans and microscopic images. Deep learning models have been widely used for supervised analysis in these experiments. Combining different image representations is frequently required to analyze and make a decision properly. Consequently, multi-view data has emerged - datasets where each sample is described by views from different angles, sources, or modalities. These problems are addressed with the concept of multi-view learning. Understanding the decision-making process of deep learning models is essential for reliable and credible analysis. Hence, many explainability methods have been devised recently. Nonetheless, there is a lack of proper explainability in multi-view models, which are challenging to explain due to their architectures. In this paper, we suggest different multi-view architectures for the vision domain, each suited to another problem, and we also present a methodology for explaining these models. To demonstrate the effectiveness of our methodology, we focus on the domain of High Energy Density Physics (HEDP) experiments, where multiple imaging representations are used to assess the quality of foam samples. We apply our methodology to classify the foam samples quality using the suggested multi-view architectures. Through experimental results, we showcase the improvement of accurate architecture choice on both accuracy - 78% to 84% and AUC - 83% to 93% and present a trade-off between performance and explainability. Specifically, we demonstrate that our approach enables the explanation of individual one-view models, providing insights into the decision-making process of each view. This understanding enhances the interpretability of the overall multi-view model. The sources of this work are available at: https://github.com/Scientific-Computing-Lab-NRCN/Multi-View-Explainability.

Abstract: Long-tailed distribution of semantic categories, which has been often ignored in conventional methods, causes unsatisfactory performance in semantic segmentation on tail categories. In this paper, we focus on the problem of long-tailed semantic segmentation. Although some long-tailed recognition methods (e.g., re-sampling/re-weighting) have been proposed in other problems, they can probably compromise crucial contextual information and are thus hardly adaptable to the problem of long-tailed semantic segmentation. To address this issue, we propose MEDOE, a novel framework for long-tailed semantic segmentation via contextual information ensemble-and-grouping. The proposed two-sage framework comprises a multi-expert decoder (MED) and a multi-expert output ensemble (MOE). Specifically, the MED includes several "experts". Based on the pixel frequency distribution, each expert takes the dataset masked according to the specific categories as input and generates contextual information self-adaptively for classification; The MOE adopts learnable decision weights for the ensemble of the experts' outputs. As a model-agnostic framework, our MEDOE can be flexibly and efficiently coupled with various popular deep neural networks (e.g., DeepLabv3+, OCRNet, and PSPNet) to improve their performance in long-tailed semantic segmentation. Experimental results show that the proposed framework outperforms the current methods on both Cityscapes and ADE20K datasets by up to 1.78% in mIoU and 5.89% in mAcc.

Abstract: This paper presents a novel network structure with illumination-aware gamma correction and complete image modelling to solve the low-light image enhancement problem. Low-light environments usually lead to less informative large-scale dark areas, directly learning deep representations from low-light images is insensitive to recovering normal illumination. We propose to integrate the effectiveness of gamma correction with the strong modelling capacities of deep networks, which enables the correction factor gamma to be learned in a coarse to elaborate manner via adaptively perceiving the deviated illumination. Because exponential operation introduces high computational complexity, we propose to use Taylor Series to approximate gamma correction, accelerating the training and inference speed. Dark areas usually occupy large scales in low-light images, common local modelling structures, e.g., CNN, SwinIR, are thus insufficient to recover accurate illumination across whole low-light images. We propose a novel Transformer block to completely simulate the dependencies of all pixels across images via a local-to-global hierarchical attention mechanism, so that dark areas could be inferred by borrowing the information from far informative regions in a highly effective manner. Extensive experiments on several benchmark datasets demonstrate that our approach outperforms state-of-the-art methods.

Abstract: Reconstructing hand-held objects from a single RGB image is an important and challenging problem. Existing works utilizing Signed Distance Fields (SDF) reveal limitations in comprehensively capturing the complex hand-object interactions, since SDF is only reliable within the proximity of the target, and hence, infeasible to simultaneously encode local hand and object cues. To address this issue, we propose DDF-HO, a novel approach leveraging Directed Distance Field (DDF) as the shape representation. Unlike SDF, DDF maps a ray in 3D space, consisting of an origin and a direction, to corresponding DDF values, including a binary visibility signal determining whether the ray intersects the objects and a distance value measuring the distance from origin to target in the given direction. We randomly sample multiple rays and collect local to global geometric features for them by introducing a novel 2D ray-based feature aggregation scheme and a 3D intersection-aware hand pose embedding, combining 2D-3D features to model hand-object interactions. Extensive experiments on synthetic and real-world datasets demonstrate that DDF-HO consistently outperforms all baseline methods by a large margin, especially under Chamfer Distance, with about 80% leap forward. Codes and trained models will be released soon.

Abstract: Detecting road lanes is challenging due to intricate markings vulnerable to unfavorable conditions. Lane markings have strong shape priors, but their visibility is easily compromised. Factors like lighting, weather, vehicles, pedestrians, and aging colors challenge the detection. A large amount of data is required to train a lane detection approach that can withstand natural variations caused by low visibility. This is because there are numerous lane shapes and natural variations that exist. Our solution, Contrastive Learning for Lane Detection via cross-similarity (CLLD), is a self-supervised learning method that tackles this challenge by enhancing lane detection models resilience to real-world conditions that cause lane low visibility. CLLD is a novel multitask contrastive learning that trains lane detection approaches to detect lane markings even in low visible situations by integrating local feature contrastive learning (CL) with our new proposed operation cross-similarity. Local feature CL focuses on extracting features for small image parts, which is necessary to localize lane segments, while cross-similarity captures global features to detect obscured lane segments using their surrounding. We enhance cross-similarity by randomly masking parts of input images for augmentation. Evaluated on benchmark datasets, CLLD outperforms state-of-the-art contrastive learning, especially in visibility-impairing conditions like shadows. Compared to supervised learning, CLLD excels in scenarios like shadows and crowded scenes.

Abstract: Automatic analysis of human behaviour is a fundamental prerequisite for the creation of machines that can effectively interact with- and support humans in social interactions. In MultiMediate'23, we address two key human social behaviour analysis tasks for the first time in a controlled challenge: engagement estimation and bodily behaviour recognition in social interactions. This paper describes the MultiMediate'23 challenge and presents novel sets of annotations for both tasks. For engagement estimation we collected novel annotations on the NOvice eXpert Interaction (NOXI) database. For bodily behaviour recognition, we annotated test recordings of the MPIIGroupInteraction corpus with the BBSI annotation scheme. In addition, we present baseline results for both challenge tasks.

Abstract: Existing methods for the 4D reconstruction of general, non-rigidly deforming objects focus on novel-view synthesis and neglect correspondences. However, time consistency enables advanced downstream tasks like 3D editing, motion analysis, or virtual-asset creation. We propose SceNeRFlow to reconstruct a general, non-rigid scene in a time-consistent manner. Our dynamic-NeRF method takes multi-view RGB videos and background images from static cameras with known camera parameters as input. It then reconstructs the deformations of an estimated canonical model of the geometry and appearance in an online fashion. Since this canonical model is time-invariant, we obtain correspondences even for long-term, long-range motions. We employ neural scene representations to parametrize the components of our method. Like prior dynamic-NeRF methods, we use a backwards deformation model. We find non-trivial adaptations of this model necessary to handle larger motions: We decompose the deformations into a strongly regularized coarse component and a weakly regularized fine component, where the coarse component also extends the deformation field into the space surrounding the object, which enables tracking over time. We show experimentally that, unlike prior work that only handles small motion, our method enables the reconstruction of studio-scale motions.

Abstract: Visual imagery is indispensable to many multi-attribute decision situations. Examples of such decision situations in travel behaviour research include residential location choices, vehicle choices, tourist destination choices, and various safety-related choices. However, current discrete choice models cannot handle image data and thus cannot incorporate information embedded in images into their representations of choice behaviour. This gap between discrete choice models' capabilities and the real-world behaviour it seeks to model leads to incomplete and, possibly, misleading outcomes. To solve this gap, this study proposes "Computer Vision-enriched Discrete Choice Models" (CV-DCMs). CV-DCMs can handle choice tasks involving numeric attributes and images by integrating computer vision and traditional discrete choice models. Moreover, because CV-DCMs are grounded in random utility maximisation principles, they maintain the solid behavioural foundation of traditional discrete choice models. We demonstrate the proposed CV-DCM by applying it to data obtained through a novel stated choice experiment involving residential location choices. In this experiment, respondents faced choice tasks with trade-offs between commute time, monthly housing cost and street-level conditions, presented using images. As such, this research contributes to the growing body of literature in the travel behaviour field that seeks to integrate discrete choice modelling and machine learning.

Abstract: The aim of audio-visual segmentation (AVS) is to precisely differentiate audible objects within videos down to the pixel level. Traditional approaches often tackle this challenge by combining information from various modalities, where the contribution of each modality is implicitly or explicitly modeled. Nevertheless, the interconnections between different modalities tend to be overlooked in audio-visual modeling. In this paper, inspired by the human ability to mentally simulate the sound of an object and its visual appearance, we introduce a bidirectional generation framework. This framework establishes robust correlations between an object's visual characteristics and its associated sound, thereby enhancing the performance of AVS. To achieve this, we employ a visual-to-audio projection component that reconstructs audio features from object segmentation masks and minimizes reconstruction errors. Moreover, recognizing that many sounds are linked to object movements, we introduce an implicit volumetric motion estimation module to handle temporal dynamics that may be challenging to capture using conventional optical flow methods. To showcase the effectiveness of our approach, we conduct comprehensive experiments and analyses on the widely recognized AVSBench benchmark. As a result, we establish a new state-of-the-art performance level in the AVS benchmark, particularly excelling in the challenging MS3 subset which involves segmenting multiple sound sources. To facilitate reproducibility, we plan to release both the source code and the pre-trained model.

Abstract: Objects are crucial for understanding human-object interactions. By identifying the relevant objects, one can also predict potential future interactions or actions that may occur with these objects. In this paper, we study the problem of Short-Term Object interaction anticipation (STA) and propose NAOGAT (Next-Active-Object Guided Anticipation Transformer), a multi-modal end-to-end transformer network, that attends to objects in observed frames in order to anticipate the next-active-object (NAO) and, eventually, to guide the model to predict context-aware future actions. The task is challenging since it requires anticipating future action along with the object with which the action occurs and the time after which the interaction will begin, a.k.a. the time to contact (TTC). Compared to existing video modeling architectures for action anticipation, NAOGAT captures the relationship between objects and the global scene context in order to predict detections for the next active object and anticipate relevant future actions given these detections, leveraging the objects' dynamics to improve accuracy. One of the key strengths of our approach, in fact, is its ability to exploit the motion dynamics of objects within a given clip, which is often ignored by other models, and separately decoding the object-centric and motion-centric information. Through our experiments, we show that our model outperforms existing methods on two separate datasets, Ego4D and EpicKitchens-100 ("Unseen Set"), as measured by several additional metrics, such as time to contact, and next-active-object localization. The code will be available upon acceptance.

Abstract: With the emerging diffusion models, recently, text-to-video generation has aroused increasing attention. But an important bottleneck therein is that generative videos often tend to carry some flickers and artifacts. In this work, we propose a dual-stream diffusion net (DSDN) to improve the consistency of content variations in generating videos. In particular, the designed two diffusion streams, video content and motion branches, could not only run separately in their private spaces for producing personalized video variations as well as content, but also be well-aligned between the content and motion domains through leveraging our designed cross-transformer interaction module, which would benefit the smoothness of generated videos. Besides, we also introduce motion decomposer and combiner to faciliate the operation on video motion. Qualitative and quantitative experiments demonstrate that our method could produce amazing continuous videos with fewer flickers.

Abstract: In recent years, discriminative self-supervised methods have made significant strides in advancing various visual tasks. The central idea of learning a data encoder that is robust to data distortions/augmentations is straightforward yet highly effective. Although many studies have demonstrated the empirical success of various learning methods, the resulting learned representations can exhibit instability and hinder downstream performance. In this study, we analyze discriminative self-supervised methods from a causal perspective to explain these unstable behaviors and propose solutions to overcome them. Our approach draws inspiration from prior works that empirically demonstrate the ability of discriminative self-supervised methods to demix ground truth causal sources to some extent. Unlike previous work on causality-empowered representation learning, we do not apply our solutions during the training process but rather during the inference process to improve time efficiency. Through experiments on both controlled image datasets and realistic image datasets, we show that our proposed solutions, which involve tempering a linear transformation with controlled synthetic data, are effective in addressing these issues.

Abstract: The goal of News Image Captioning is to generate an image caption according to the content of both a news article and an image. To leverage the visual information effectively, it is important to exploit the connection between the context in the articles/captions and the images. Psychological studies indicate that human faces in images draw higher attention priorities. On top of that, humans often play a central role in news stories, as also proven by the face-name co-occurrence pattern we discover in existing News Image Captioning datasets. Therefore, we design a face-naming module for faces in images and names in captions/articles to learn a better name embedding. Apart from names, which can be directly linked to an image area (faces), news image captions mostly contain context information that can only be found in the article. Humans typically address this by searching for relevant information from the article based on the image. To emulate this thought process, we design a retrieval strategy using CLIP to retrieve sentences that are semantically close to the image. We conduct extensive experiments to demonstrate the efficacy of our framework. Without using additional paired data, we establish the new state-of-the-art performance on two News Image Captioning datasets, exceeding the previous state-of-the-art by 5 CIDEr points. We will release code upon acceptance.

Abstract: Raw videos have been proven to own considerable feature redundancy where in many cases only a portion of frames can already meet the requirements for accurate recognition. In this paper, we are interested in whether such redundancy can be effectively leveraged to facilitate efficient inference in continuous sign language recognition (CSLR). We propose a novel adaptive model (AdaBrowse) to dynamically select a most informative subsequence from input video sequences by modelling this problem as a sequential decision task. In specific, we first utilize a lightweight network to quickly scan input videos to extract coarse features. Then these features are fed into a policy network to intelligently select a subsequence to process. The corresponding subsequence is finally inferred by a normal CSLR model for sentence prediction. As only a portion of frames are processed in this procedure, the total computations can be considerably saved. Besides temporal redundancy, we are also interested in whether the inherent spatial redundancy can be seamlessly integrated together to achieve further efficiency, i.e., dynamically selecting a lowest input resolution for each sample, whose model is referred to as AdaBrowse+. Extensive experimental results on four large-scale CSLR datasets, i.e., PHOENIX14, PHOENIX14-T, CSL-Daily and CSL, demonstrate the effectiveness of AdaBrowse and AdaBrowse+ by achieving comparable accuracy with state-of-the-art methods with 1.44$\times$ throughput and 2.12$\times$ fewer FLOPs. Comparisons with other commonly-used 2D CNNs and adaptive efficient methods verify the effectiveness of AdaBrowse. Code is available at \url{https://github.com/hulianyuyy/AdaBrowse}.

Abstract: Monocular depth estimation is an ongoing challenge in computer vision. Recent progress with Transformer models has demonstrated notable advantages over conventional CNNs in this area. However, there's still a gap in understanding how these models prioritize different regions in 2D images and how these regions affect depth estimation performance. To explore the differences between Transformers and CNNs, we employ a sparse pixel approach to contrastively analyze the distinctions between the two. Our findings suggest that while Transformers excel in handling global context and intricate textures, they lag behind CNNs in preserving depth gradient continuity. To further enhance the performance of Transformer models in monocular depth estimation, we propose the Depth Gradient Refinement (DGR) module that refines depth estimation through high-order differentiation, feature fusion, and recalibration. Additionally, we leverage optimal transport theory, treating depth maps as spatial probability distributions, and employ the optimal transport distance as a loss function to optimize our model. Experimental results demonstrate that models integrated with the plug-and-play Depth Gradient Refinement (DGR) module and the proposed loss function enhance performance without increasing complexity and computational costs. This research not only offers fresh insights into the distinctions between Transformers and CNNs in depth estimation but also paves the way for novel depth estimation methodologies.

Abstract: As one of the energy-efficient alternatives of conventional neural networks (CNNs), spiking neural networks (SNNs) have gained more and more interest recently. To train the deep models, some effective batch normalization (BN) techniques are proposed in SNNs. All these BNs are suggested to be used after the convolution layer as usually doing in CNNs. However, the spiking neuron is much more complex with the spatio-temporal dynamics. The regulated data flow after the BN layer will be disturbed again by the membrane potential updating operation before the firing function, i.e., the nonlinear activation. Therefore, we advocate adding another BN layer before the firing function to normalize the membrane potential again, called MPBN. To eliminate the induced time cost of MPBN, we also propose a training-inference-decoupled re-parameterization technique to fold the trained MPBN into the firing threshold. With the re-parameterization technique, the MPBN will not introduce any extra time burden in the inference. Furthermore, the MPBN can also adopt the element-wised form, while these BNs after the convolution layer can only use the channel-wised form. Experimental results show that the proposed MPBN performs well on both popular non-spiking static and neuromorphic datasets. Our code is open-sourced at \href{https://github.com/yfguo91/MPBN}{MPBN}.

Abstract: Dynamic convolution learns a linear mixture of $n$ static kernels weighted with their sample-dependent attentions, demonstrating superior performance compared to normal convolution. However, existing designs are parameter-inefficient: they increase the number of convolutional parameters by $n$ times. This and the optimization difficulty lead to no research progress in dynamic convolution that can allow us to use a significant large value of $n$ (e.g., $n>100$ instead of typical setting $n<10$) to push forward the performance boundary. In this paper, we propose $KernelWarehouse$, a more general form of dynamic convolution, which can strike a favorable trade-off between parameter efficiency and representation power. Its key idea is to redefine the basic concepts of "$kernels$" and "$assembling$ $kernels$" in dynamic convolution from the perspective of reducing kernel dimension and increasing kernel number significantly. In principle, KernelWarehouse enhances convolutional parameter dependencies within the same layer and across successive layers via tactful kernel partition and warehouse sharing, yielding a high degree of freedom to fit a desired parameter budget. We validate our method on ImageNet and MS-COCO datasets with different ConvNet architectures, and show that it attains state-of-the-art results. For instance, the ResNet18|ResNet50|MobileNetV2|ConvNeXt-Tiny model trained with KernelWarehouse on ImageNet reaches 76.05%|81.05%|75.52%|82.51% top-1 accuracy. Thanks to its flexible design, KernelWarehouse can even reduce the model size of a ConvNet while improving the accuracy, e.g., our ResNet18 model with 36.45%|65.10% parameter reduction to the baseline shows 2.89%|2.29% absolute improvement to top-1 accuracy.

Abstract: We propose an agglomerative Transformer (AGER) that enables Transformer-based human-object interaction (HOI) detectors to flexibly exploit extra instance-level cues in a single-stage and end-to-end manner for the first time. AGER acquires instance tokens by dynamically clustering patch tokens and aligning cluster centers to instances with textual guidance, thus enjoying two benefits: 1) Integrality: each instance token is encouraged to contain all discriminative feature regions of an instance, which demonstrates a significant improvement in the extraction of different instance-level cues and subsequently leads to a new state-of-the-art performance of HOI detection with 36.75 mAP on HICO-Det. 2) Efficiency: the dynamical clustering mechanism allows AGER to generate instance tokens jointly with the feature learning of the Transformer encoder, eliminating the need of an additional object detector or instance decoder in prior methods, thus allowing the extraction of desirable extra cues for HOI detection in a single-stage and end-to-end pipeline. Concretely, AGER reduces GFLOPs by 8.5% and improves FPS by 36%, even compared to a vanilla DETR-like pipeline without extra cue extraction.

Abstract: A growing need exists for efficient and accurate methods for detecting defects in semiconductor materials and devices. These defects can have a detrimental impact on the efficiency of the manufacturing process, because they cause critical failures and wafer-yield limitations. As nodes and patterns get smaller, even high-resolution imaging techniques such as Scanning Electron Microscopy (SEM) produce noisy images due to operating close to sensitivity levels and due to varying physical properties of different underlayers or resist materials. This inherent noise is one of the main challenges for defect inspection. One promising approach is the use of machine learning algorithms, which can be trained to accurately classify and locate defects in semiconductor samples. Recently, convolutional neural networks have proved to be particularly useful in this regard. This systematic review provides a comprehensive overview of the state of automated semiconductor defect inspection on SEM images, including the most recent innovations and developments. 38 publications were selected on this topic, indexed in IEEE Xplore and SPIE databases. For each of these, the application, methodology, dataset, results, limitations and future work were summarized. A comprehensive overview and analysis of their methods is provided. Finally, promising avenues for future work in the field of SEM-based defect inspection are suggested.

Abstract: We propose a novel mixed-integer programming (MIP) formulation for generating precise sparse correspondences for highly non-rigid shapes. To this end, we introduce a projected Laplace-Beltrami operator (PLBO) which combines intrinsic and extrinsic geometric information to measure the deformation quality induced by predicted correspondences. We integrate the PLBO, together with an orientation-aware regulariser, into a novel MIP formulation that can be solved to global optimality for many practical problems. In contrast to previous methods, our approach is provably invariant to rigid transformations and global scaling, initialisation-free, has optimality guarantees, and scales to high resolution meshes with (empirically observed) linear time. We show state-of-the-art results for sparse non-rigid matching on several challenging 3D datasets, including data with inconsistent meshing, as well as applications in mesh-to-point-cloud matching.

Abstract: Video-language pre-trained models have shown remarkable success in guiding video question-answering (VideoQA) tasks. However, due to the length of video sequences, training large-scale video-based models incurs considerably higher costs than training image-based ones. This motivates us to leverage the knowledge from image-based pretraining, despite the obvious gaps between image and video domains. To bridge these gaps, in this paper, we propose Tem-Adapter, which enables the learning of temporal dynamics and complex semantics by a visual Temporal Aligner and a textual Semantic Aligner. Unlike conventional pretrained knowledge adaptation methods that only concentrate on the downstream task objective, the Temporal Aligner introduces an extra language-guided autoregressive task aimed at facilitating the learning of temporal dependencies, with the objective of predicting future states based on historical clues and language guidance that describes event progression. Besides, to reduce the semantic gap and adapt the textual representation for better event description, we introduce a Semantic Aligner that first designs a template to fuse question and answer pairs as event descriptions and then learns a Transformer decoder with the whole video sequence as guidance for refinement. We evaluate Tem-Adapter and different pre-train transferring methods on two VideoQA benchmarks, and the significant performance improvement demonstrates the effectiveness of our method.

Abstract: Contrastive Language-Image Pre-training (CLIP) has significantly boosted the performance of various vision-language tasks by scaling up the dataset with image-text pairs collected from the web. However, the presence of intrinsic noise and unmatched image-text pairs in web data can potentially affect the performance of representation learning. To address this issue, we first utilize the OFA model to generate synthetic captions that focus on the image content. The generated captions contain complementary information that is beneficial for pre-training. Then, we propose an Adaptive Language-Image Pre-training (ALIP), a bi-path model that integrates supervision from both raw text and synthetic caption. As the core components of ALIP, the Language Consistency Gate (LCG) and Description Consistency Gate (DCG) dynamically adjust the weights of samples and image-text/caption pairs during the training process. Meanwhile, the adaptive contrastive loss can effectively reduce the impact of noise data and enhances the efficiency of pre-training data. We validate ALIP with experiments on different scales of models and pre-training datasets. Experiments results show that ALIP achieves state-of-the-art performance on multiple downstream tasks including zero-shot image-text retrieval and linear probe. To facilitate future research, the code and pre-trained models are released at https://github.com/deepglint/ALIP.

Abstract: Most of the research in content-based image retrieval (CBIR) focus on developing robust feature representations that can effectively retrieve instances from a database of images that are visually similar to a query. However, the retrieved images sometimes contain results that are not semantically related to the query. To address this, we propose a method for CBIR that captures both visual and semantic similarity using a visual hierarchy. The hierarchy is constructed by merging classes with overlapping features in the latent space of a deep neural network trained for classification, assuming that overlapping classes share high visual and semantic similarities. Finally, the constructed hierarchy is integrated into the distance calculation metric for similarity search. Experiments on standard datasets: CUB-200-2011 and CIFAR100, and a real-life use case using diatom microscopy images show that our method achieves superior performance compared to the existing methods on image retrieval.

Abstract: The extraction of lakes from remote sensing images is a complex challenge due to the varied lake shapes and data noise. Current methods rely on multispectral image datasets, making it challenging to learn lake features accurately from pixel arrangements. This, in turn, affects model learning and the creation of accurate segmentation masks. This paper introduces a unified prompt-based dataset construction approach that provides approximate lake locations using point, box, and mask prompts. We also propose a two-stage prompt enhancement framework, LEPrompter, which involves prompt-based and prompt-free stages during training. The prompt-based stage employs a prompt encoder to extract prior information, integrating prompt tokens and image embeddings through self- and cross-attention in the prompt decoder. Prompts are deactivated once the model is trained to ensure independence during inference, enabling automated lake extraction. Evaluations on Surface Water and Qinghai-Tibet Plateau Lake datasets show consistent performance improvements compared to the previous state-of-the-art method. LEPrompter achieves mIoU scores of 91.48% and 97.43% on the respective datasets without introducing additional parameters or GFLOPs. Supplementary materials provide the source code, pre-trained models, and detailed user studies.

Abstract: In object detection, the cost of labeling is much high because it needs not only to confirm the categories of multiple objects in an image but also to accurately determine the bounding boxes of each object. Thus, integrating active learning into object detection will raise pretty positive significance. In this paper, we propose a classification committee for active deep object detection method by introducing a discrepancy mechanism of multiple classifiers for samples' selection when training object detectors. The model contains a main detector and a classification committee. The main detector denotes the target object detector trained from a labeled pool composed of the selected informative images. The role of the classification committee is to select the most informative images according to their uncertainty values from the view of classification, which is expected to focus more on the discrepancy and representative of instances. Specifically, they compute the uncertainty for a specified instance within the image by measuring its discrepancy output by the committee pre-trained via the proposed Maximum Classifiers Discrepancy Group Loss (MCDGL). The most informative images are finally determined by selecting the ones with many high-uncertainty instances. Besides, to mitigate the impact of interference instances, we design a Focus on Positive Instances Loss (FPIL) to make the committee the ability to automatically focus on the representative instances as well as precisely encode their discrepancies for the same instance. Experiments are conducted on Pascal VOC and COCO datasets versus some popular object detectors. And results show that our method outperforms the state-of-the-art active learning methods, which verifies the effectiveness of the proposed method.

Abstract: Keypoint detection is a pivotal step in 3D reconstruction, whereby sets of (up to) K points are detected in each view of a scene. Crucially, the detected points need to be consistent between views, i.e., correspond to the same 3D point in the scene. One of the main challenges with keypoint detection is the formulation of the learning objective. Previous learning-based methods typically jointly learn descriptors with keypoints, and treat the keypoint detection as a binary classification task on mutual nearest neighbours. However, basing keypoint detection on descriptor nearest neighbours is a proxy task, which is not guaranteed to produce 3D-consistent keypoints. Furthermore, this ties the keypoints to a specific descriptor, complicating downstream usage. In this work, we instead learn keypoints directly from 3D consistency. To this end, we train the detector to detect tracks from large-scale SfM. As these points are often overly sparse, we derive a semi-supervised two-view detection objective to expand this set to a desired number of detections. To train a descriptor, we maximize the mutual nearest neighbour objective over the keypoints with a separate network. Results show that our approach, DeDoDe, achieves significant gains on multiple geometry benchmarks. Code is provided at https://github.com/Parskatt/DeDoDe .

Abstract: Camera-based perception systems play a central role in modern autonomous vehicles. These camera based perception algorithms require an accurate calibration to map the real world distances to image pixels. In practice, calibration is a laborious procedure requiring specialised data collection and careful tuning. This process must be repeated whenever the parameters of the camera change, which can be a frequent occurrence in autonomous vehicles. Hence there is a need to calibrate at regular intervals to ensure the camera is accurate. Proposed is a deep learning framework to learn intrinsic and extrinsic calibration of the camera in real time. The framework is self-supervised and doesn't require any labelling or supervision to learn the calibration parameters. The framework learns calibration without the need for any physical targets or to drive the car on special planar surfaces.

Abstract: Traditional geometric registration based estimation methods only exploit the CAD model implicitly, which leads to their dependence on observation quality and deficiency to occlusion.To address the problem,the paper proposes a bidirectional correspondence prediction network with a point-wise attention-aware mechanism. This network not only requires the model points to predict the correspondence but also explicitly models the geometric similarities between observations and the model prior.} Our key insight is that the correlations between each model point and scene point provide essential information for learning point-pair matches. To further tackle the correlation noises brought by feature distribution divergence, we design a simple but effective pseudo-siamese network to improve feature homogeneity.Experimental results on the public datasets of LineMOD, YCB-Video, and Occ-LineMOD show that the proposed method achieves better performance than other state-of-the-art methods under the same evaluation criteria. Its robustness in estimating poses is greatly improved, especially in an environment with severe occlusions.

Abstract: Large language models (LLMs) have made tremendous progress in natural language understanding and they have also been successfully adopted in other domains such as computer vision, robotics, reinforcement learning, etc. In this work, we apply LLMs to image generation tasks by directly generating the virtual brush strokes to paint an image. We present Painter, an LLM that can convert user prompts in text description format to sketches by generating the corresponding brush strokes in an auto-regressive way. We construct Painter based on off-the-shelf LLM that is pre-trained on a large text corpus, by fine-tuning it on the new task while preserving language understanding capabilities. We create a dataset of diverse multi-object sketches paired with textual prompts that covers several object types and tasks. Painter can generate sketches from text descriptions, remove objects from canvas, and detect and classify objects in sketches. Although this is an unprecedented pioneering work in using LLMs for auto-regressive image generation, the results are very encouraging.

Abstract: Text-to-image synthesis has made encouraging progress and attracted lots of public attention recently. However, popular evaluation metrics in this area, like the Inception Score and Fr'echet Inception Distance, incur several issues. First of all, they cannot explicitly assess the perceptual quality of generated images and poorly reflect the semantic alignment of each text-image pair. Also, they are inefficient and need to sample thousands of images to stabilise their evaluation results. In this paper, we propose to evaluate text-to-image generation performance by directly estimating the likelihood of the generated images using a pre-trained likelihood-based text-to-image generative model, i.e., a higher likelihood indicates better perceptual quality and better text-image alignment. To prevent the likelihood of being dominated by the non-crucial part of the generated image, we propose several new designs to develop a credit assignment strategy based on the semantic and perceptual significance of the image patches. In the experiments, we evaluate the proposed metric on multiple popular text-to-image generation models and datasets in accessing both the perceptual quality and the text-image alignment. Moreover, it can successfully assess the generation ability of these models with as few as a hundred samples, making it very efficient in practice.

Abstract: Although we have witnessed significant progress in human-object interaction (HOI) detection with increasingly high mAP (mean Average Precision), a single mAP score is too concise to obtain an informative summary of a model's performance and to understand why one approach is better than another. In this paper, we introduce a diagnosis toolbox for analyzing the error sources of the existing HOI detection models. We first conduct holistic investigations in the pipeline of HOI detection, consisting of human-object pair detection and then interaction classification. We define a set of errors and the oracles to fix each of them. By measuring the mAP improvement obtained from fixing an error using its oracle, we can have a detailed analysis of the significance of different errors. We then delve into the human-object detection and interaction classification, respectively, and check the model's behavior. For the first detection task, we investigate both recall and precision, measuring the coverage of ground-truth human-object pairs as well as the noisiness level in the detections. For the second classification task, we compute mAP for interaction classification only, without considering the detection scores. We also measure the performance of the models in differentiating human-object pairs with and without actual interactions using the AP (Average Precision) score. Our toolbox is applicable for different methods across different datasets and available at https://github.com/neu-vi/Diag-HOI.

Abstract: Neural Radiance Fields (NeRFs) have revolutionized the field of novel view synthesis, demonstrating remarkable performance. However, the modeling and rendering of reflective objects remain challenging problems. Recent methods have shown significant improvements over the baselines in handling reflective scenes, albeit at the expense of efficiency. In this work, we aim to strike a balance between efficiency and quality. To this end, we investigate an implicit-explicit approach based on conventional volume rendering to enhance the reconstruction quality and accelerate the training and rendering processes. We adopt an efficient density-based grid representation and reparameterize the reflected radiance in our pipeline. Our proposed reflection-aware approach achieves a competitive quality efficiency trade-off compared to competing methods. Based on our experimental results, we propose and discuss hypotheses regarding the factors influencing the results of density-based methods for reconstructing reflective objects. The source code is available at: https://github.com/gkouros/ref-dvgo

Abstract: Vectorized high-definition (HD) maps contain detailed information about surrounding road elements, which are crucial for various downstream tasks in modern autonomous driving vehicles, such as vehicle planning and control. Recent works have attempted to directly detect the vectorized HD map as a point set prediction task, resulting in significant improvements in detection performance. However, these approaches fail to analyze and exploit the inner-instance correlations between predicted points, impeding further advancements. To address these challenges, we investigate the utilization of inner-$\textbf{INS}$tance information for vectorized h$\textbf{IGH}$-definition mapping through $\textbf{T}$ransformers and introduce InsightMapper. This paper presents three novel designs within InsightMapper that leverage inner-instance information in distinct ways, including hybrid query generation, inner-instance query fusion, and inner-instance feature aggregation. Comparative experiments are conducted on the NuScenes dataset, showcasing the superiority of our proposed method. InsightMapper surpasses previous state-of-the-art (SOTA) methods by 5.78 mAP and 5.12 TOPO, which assess topology correctness. Simultaneously, InsightMapper maintains high efficiency during both training and inference phases, resulting in remarkable comprehensive performance. The project page for this work is available at https://tonyxuqaq.github.io/projects/InsightMapper .

Abstract: This paper strives for motion expressions guided video segmentation, which focuses on segmenting objects in video content based on a sentence describing the motion of the objects. Existing referring video object datasets typically focus on salient objects and use language expressions that contain excessive static attributes that could potentially enable the target object to be identified in a single frame. These datasets downplay the importance of motion in video content for language-guided video object segmentation. To investigate the feasibility of using motion expressions to ground and segment objects in videos, we propose a large-scale dataset called MeViS, which contains numerous motion expressions to indicate target objects in complex environments. We benchmarked 5 existing referring video object segmentation (RVOS) methods and conducted a comprehensive comparison on the MeViS dataset. The results show that current RVOS methods cannot effectively address motion expression-guided video segmentation. We further analyze the challenges and propose a baseline approach for the proposed MeViS dataset. The goal of our benchmark is to provide a platform that enables the development of effective language-guided video segmentation algorithms that leverage motion expressions as a primary cue for object segmentation in complex video scenes. The proposed MeViS dataset has been released at https://henghuiding.github.io/MeViS.

Abstract: Despite recent research advancements in reconstructing clothed humans from a single image, accurately restoring the "unseen regions" with high-level details remains an unsolved challenge that lacks attention. Existing methods often generate overly smooth back-side surfaces with a blurry texture. But how to effectively capture all visual attributes of an individual from a single image, which are sufficient to reconstruct unseen areas (e.g., the back view)? Motivated by the power of foundation models, TeCH reconstructs the 3D human by leveraging 1) descriptive text prompts (e.g., garments, colors, hairstyles) which are automatically generated via a garment parsing model and Visual Question Answering (VQA), 2) a personalized fine-tuned Text-to-Image diffusion model (T2I) which learns the "indescribable" appearance. To represent high-resolution 3D clothed humans at an affordable cost, we propose a hybrid 3D representation based on DMTet, which consists of an explicit body shape grid and an implicit distance field. Guided by the descriptive prompts + personalized T2I diffusion model, the geometry and texture of the 3D humans are optimized through multi-view Score Distillation Sampling (SDS) and reconstruction losses based on the original observation. TeCH produces high-fidelity 3D clothed humans with consistent & delicate texture, and detailed full-body geometry. Quantitative and qualitative experiments demonstrate that TeCH outperforms the state-of-the-art methods in terms of reconstruction accuracy and rendering quality. The code will be publicly available for research purposes at https://huangyangyi.github.io/tech