Computer Vision and Pattern Recognition (cs.CV)

Abstract: Dense SLAM based on monocular cameras does indeed have immense application value in the field of AR/VR, especially when it is performed on a mobile device. In this paper, we propose a novel method that integrates a light-weight depth completion network into a sparse SLAM system using a multi-basis depth representation, so that dense mapping can be performed online even on a mobile phone. Specifically, we present a specifically optimized multi-basis depth completion network, called BBC-Net, tailored to the characteristics of traditional sparse SLAM systems. BBC-Net can predict multiple balanced bases and a confidence map from a monocular image with sparse points generated by off-the-shelf keypoint-based SLAM systems. The final depth is a linear combination of predicted depth bases that can be optimized by tuning the corresponding weights. To seamlessly incorporate the weights into traditional SLAM optimization and ensure efficiency and robustness, we design a set of depth weight factors, which makes our network a versatile plug-in module, facilitating easy integration into various existing sparse SLAM systems and significantly enhancing global depth consistency through bundle adjustment. To verify the portability of our method, we integrate BBC-Net into two representative SLAM systems. The experimental results on various datasets show that the proposed method achieves better performance in monocular dense mapping than the state-of-the-art methods. We provide an online demo running on a mobile phone, which verifies the efficiency and mapping quality of the proposed method in real-world scenarios.

Abstract: Visual odometry (VO) and SLAM have been using multi-view geometry via local structure from motion for decades. These methods have a slight disadvantage in challenging scenarios such as low-texture images, dynamic scenarios, etc. Meanwhile, use of deep neural networks to extract high level features is ubiquitous in computer vision. For VO, we can use these deep networks to extract depth and pose estimates using these high level features. The visual odometry task then can be modeled as an image generation task where the pose estimation is the by-product. This can also be achieved in a self-supervised manner, thereby eliminating the data (supervised) intensive nature of training deep neural networks. Although some works tried the similar approach [1], the depth and pose estimation in the previous works are vague sometimes resulting in accumulation of error (drift) along the trajectory. The goal of this work is to tackle these limitations of past approaches and to develop a method that can provide better depths and pose estimates. To address this, a couple of approaches are explored: 1) Modeling: Using optical flow and recurrent neural networks (RNN) in order to exploit spatio-temporal correlations which can provide more information to estimate depth. 2) Loss function: Generative adversarial network (GAN) [2] is deployed to improve the depth estimation (and thereby pose too), as shown in Figure 1. This additional loss term improves the realism in generated images and reduces artifacts.

Abstract: Self-supervised learning (SSL) using mixed images has been studied to learn various image representations. Existing methods using mixed images learn a representation by maximizing the similarity between the representation of the mixed image and the synthesized representation of the original images. However, few methods consider the synthesis of representations from the perspective of mathematical logic. In this study, we focused on a synthesis method of representations. We proposed a new SSL with mixed images and a new representation format based on many-valued logic. This format can indicate the feature-possession degree, that is, how much of each image feature is possessed by a representation. This representation format and representation synthesis by logic operation realize that the synthesized representation preserves the remarkable characteristics of the original representations. Our method performed competitively with previous representation synthesis methods for image classification tasks. We also examined the relationship between the feature-possession degree and the number of classes of images in the multilabel image classification dataset to verify that the intended learning was achieved. In addition, we discussed image retrieval, which is an application of our proposed representation format using many-valued logic.

Abstract: Existing approaches to modeling associations between visual stimuli and brain responses are facing difficulties in handling between-subject variance and model generalization. Inspired by the recent progress in modeling speech-brain response, we propose in this work a ``match-vs-mismatch'' deep learning model to classify whether a video clip induces excitatory responses in recorded EEG signals and learn associations between the visual content and corresponding neural recordings. Using an exclusive experimental dataset, we demonstrate that the proposed model is able to achieve the highest accuracy on unseen subjects as compared to other baseline models. Furthermore, we analyze the inter-subject noise using a subject-level silhouette score in the embedding space and show that the developed model is able to mitigate inter-subject noise and significantly reduce the silhouette score. Moreover, we examine the Grad-CAM activation score and show that the brain regions associated with language processing contribute most to the model predictions, followed by regions associated with visual processing. These results have the potential to facilitate the development of neural recording-based video reconstruction and its related applications.

Abstract: Large-scale vision-language models (VLMs), e.g., CLIP, learn broad visual concepts from tedious training data, showing superb generalization ability. Amount of prompt learning methods have been proposed to efficiently adapt the VLMs to downstream tasks with only a few training samples. We introduce a novel method to improve the prompt learning of vision-language models by incorporating pre-trained large language models (LLMs), called Dual-Aligned Prompt Tuning (DuAl-PT). Learnable prompts, like CoOp, implicitly model the context through end-to-end training, which are difficult to control and interpret. While explicit context descriptions generated by LLMs, like GPT-3, can be directly used for zero-shot classification, such prompts are overly relying on LLMs and still underexplored in few-shot domains. With DuAl-PT, we propose to learn more context-aware prompts, benefiting from both explicit and implicit context modeling. To achieve this, we introduce a pre-trained LLM to generate context descriptions, and we encourage the prompts to learn from the LLM's knowledge by alignment, as well as the alignment between prompts and local image features. Empirically, DuAl-PT achieves superior performance on 11 downstream datasets on few-shot recognition and base-to-new generalization. Hopefully, DuAl-PT can serve as a strong baseline. Code will be available.

Abstract: Geodesic models are known as an efficient tool for solving various image segmentation problems. Most of existing approaches only exploit local pointwise image features to track geodesic paths for delineating the objective boundaries. However, such a segmentation strategy cannot take into account the connectivity of the image edge features, increasing the risk of shortcut problem, especially in the case of complicated scenario. In this work, we introduce a new image segmentation model based on the minimal geodesic framework in conjunction with an adaptive cut-based circular optimal path computation scheme and a graph-based boundary proposals grouping scheme. Specifically, the adaptive cut can disconnect the image domain such that the target contours are imposed to pass through this cut only once. The boundary proposals are comprised of precomputed image edge segments, providing the connectivity information for our segmentation model. These boundary proposals are then incorporated into the proposed image segmentation model, such that the target segmentation contours are made up of a set of selected boundary proposals and the corresponding geodesic paths linking them. Experimental results show that the proposed model indeed outperforms state-of-the-art minimal paths-based image segmentation approaches.

Abstract: The problem of phase retrieval (PR) involves recovering an unknown image from limited amplitude measurement data and is a challenge nonlinear inverse problem in computational imaging and image processing. However, many of the PR methods are based on black-box network models that lack interpretability and plug-and-play (PnP) frameworks that are computationally complex and require careful parameter tuning. To address this, we have developed PRISTA-Net, a deep unfolding network (DUN) based on the first-order iterative shrinkage thresholding algorithm (ISTA). This network utilizes a learnable nonlinear transformation to address the proximal-point mapping sub-problem associated with the sparse priors, and an attention mechanism to focus on phase information containing image edges, textures, and structures. Additionally, the fast Fourier transform (FFT) is used to learn global features to enhance local information, and the designed logarithmic-based loss function leads to significant improvements when the noise level is low. All parameters in the proposed PRISTA-Net framework, including the nonlinear transformation, threshold parameters, and step size, are learned end-to-end instead of being manually set. This method combines the interpretability of traditional methods with the fast inference ability of deep learning and is able to handle noise at each iteration during the unfolding stage, thus improving recovery quality. Experiments on Coded Diffraction Patterns (CDPs) measurements demonstrate that our approach outperforms the existing state-of-the-art methods in terms of qualitative and quantitative evaluations. Our source codes are available at \emph{https://github.com/liuaxou/PRISTA-Net}.

Abstract: We propose a novel unsupervised object localization method that allows us to explain the predictions of the model by utilizing self-supervised pre-trained models without additional finetuning. Existing unsupervised and self-supervised object localization methods often utilize class-agnostic activation maps or self-similarity maps of a pre-trained model. Although these maps can offer valuable information for localization, their limited ability to explain how the model makes predictions remains challenging. In this paper, we propose a simple yet effective unsupervised object localization method based on representer point selection, where the predictions of the model can be represented as a linear combination of representer values of training points. By selecting representer points, which are the most important examples for the model predictions, our model can provide insights into how the model predicts the foreground object by providing relevant examples as well as their importance. Our method outperforms the state-of-the-art unsupervised and self-supervised object localization methods on various datasets with significant margins and even outperforms recent weakly supervised and few-shot methods.

Abstract: Real-time Stereo Matching is a cornerstone algorithm for many Extended Reality (XR) applications, such as indoor 3D understanding, video pass-through, and mixed-reality games. Despite significant advancements in deep stereo methods, achieving real-time depth inference with high accuracy on a low-power device remains a major challenge. One of the major difficulties is the lack of high-quality indoor video stereo training datasets captured by head-mounted VR/AR glasses. To address this issue, we introduce a novel video stereo synthetic dataset that comprises photorealistic renderings of various indoor scenes and realistic camera motion captured by a 6-DoF moving VR/AR head-mounted display (HMD). This facilitates the evaluation of existing approaches and promotes further research on indoor augmented reality scenarios. Our newly proposed dataset enables us to develop a novel framework for continuous video-rate stereo matching. As another contribution, our dataset enables us to proposed a new video-based stereo matching approach tailored for XR applications, which achieves real-time inference at an impressive 134fps on a standard desktop computer, or 30fps on a battery-powered HMD. Our key insight is that disparity and contextual information are highly correlated and redundant between consecutive stereo frames. By unrolling an iterative cost aggregation in time (i.e. in the temporal dimension), we are able to distribute and reuse the aggregated features over time. This approach leads to a substantial reduction in computation without sacrificing accuracy. We conducted extensive evaluations and comparisons and demonstrated that our method achieves superior performance compared to the current state-of-the-art, making it a strong contender for real-time stereo matching in VR/AR applications.

Abstract: Autonomous 3D part assembly is a challenging task in the areas of robotics and 3D computer vision. This task aims to assemble individual components into a complete shape without relying on predefined instructions. In this paper, we formulate this task from a novel generative perspective, introducing the Score-based 3D Part Assembly framework (Score-PA) for 3D part assembly. Knowing that score-based methods are typically time-consuming during the inference stage. To address this issue, we introduce a novel algorithm called the Fast Predictor-Corrector Sampler (FPC) that accelerates the sampling process within the framework. We employ various metrics to assess assembly quality and diversity, and our evaluation results demonstrate that our algorithm outperforms existing state-of-the-art approaches. We release our code at https://github.com/J-F-Cheng/Score-PA_Score-based-3D-Part-Assembly.

Abstract: Long-range dependency modeling has been widely considered in modern deep learning based semantic segmentation methods, especially those designed for large-size remote sensing images, to compensate the intrinsic locality of standard convolutions. However, in previous studies, the long-range dependency, modeled with an attention mechanism or transformer model, has been based on unsupervised learning, instead of explicit supervision from the objective ground truth. In this paper, we propose a novel supervised long-range correlation method for land-cover classification, called the supervised long-range correlation network (SLCNet), which is shown to be superior to the currently used unsupervised strategies. In SLCNet, pixels sharing the same category are considered highly correlated and those having different categories are less relevant, which can be easily supervised by the category consistency information available in the ground truth semantic segmentation map. Under such supervision, the recalibrated features are more consistent for pixels of the same category and more discriminative for pixels of other categories, regardless of their proximity. To complement the detailed information lacking in the global long-range correlation, we introduce an auxiliary adaptive receptive field feature extraction module, parallel to the long-range correlation module in the encoder, to capture finely detailed feature representations for multi-size objects in multi-scale remote sensing images. In addition, we apply multi-scale side-output supervision and a hybrid loss function as local and global constraints to further boost the segmentation accuracy. Experiments were conducted on three remote sensing datasets. Compared with the advanced segmentation methods from the computer vision, medicine, and remote sensing communities, the SLCNet achieved a state-of-the-art performance on all the datasets.

Abstract: In this paper, we present a new approach for facial anonymization in images and videos, abbreviated as FIVA. Our proposed method is able to maintain the same face anonymization consistently over frames with our suggested identity-tracking and guarantees a strong difference from the original face. FIVA allows for 0 true positives for a false acceptance rate of 0.001. Our work considers the important security issue of reconstruction attacks and investigates adversarial noise, uniform noise, and parameter noise to disrupt reconstruction attacks. In this regard, we apply different defense and protection methods against these privacy threats to demonstrate the scalability of FIVA. On top of this, we also show that reconstruction attack models can be used for detection of deep fakes. Last but not least, we provide experimental results showing how FIVA can even enable face swapping, which is purely trained on a single target image.

Abstract: In this paper, we propose a novel framework, Tracking-free Relightable Avatar (TRAvatar), for capturing and reconstructing high-fidelity 3D avatars. Compared to previous methods, TRAvatar works in a more practical and efficient setting. Specifically, TRAvatar is trained with dynamic image sequences captured in a Light Stage under varying lighting conditions, enabling realistic relighting and real-time animation for avatars in diverse scenes. Additionally, TRAvatar allows for tracking-free avatar capture and obviates the need for accurate surface tracking under varying illumination conditions. Our contributions are two-fold: First, we propose a novel network architecture that explicitly builds on and ensures the satisfaction of the linear nature of lighting. Trained on simple group light captures, TRAvatar can predict the appearance in real-time with a single forward pass, achieving high-quality relighting effects under illuminations of arbitrary environment maps. Second, we jointly optimize the facial geometry and relightable appearance from scratch based on image sequences, where the tracking is implicitly learned. This tracking-free approach brings robustness for establishing temporal correspondences between frames under different lighting conditions. Extensive qualitative and quantitative experiments demonstrate that our framework achieves superior performance for photorealistic avatar animation and relighting.

Abstract: In the life cycle of highly automated systems operating in an open and dynamic environment, the ability to adjust to emerging challenges is crucial. For systems integrating data-driven AI-based components, rapid responses to deployment issues require fast access to related data for testing and reconfiguration. In the context of automated driving, this especially applies to road obstacles that were not included in the training data, commonly referred to as out-of-distribution (OoD) road obstacles. Given the availability of large uncurated recordings of driving scenes, a pragmatic approach is to query a database to retrieve similar scenarios featuring the same safety concerns due to OoD road obstacles. In this work, we extend beyond identifying OoD road obstacles in video streams and offer a comprehensive approach to extract sequences of OoD road obstacles using text queries, thereby proposing a way of curating a collection of OoD data for subsequent analysis. Our proposed method leverages the recent advances in OoD segmentation and multi-modal foundation models to identify and efficiently extract safety-relevant scenes from unlabeled videos. We present a first approach for the novel task of text-based OoD object retrieval, which addresses the question ''Have we ever encountered this before?''.

Abstract: Self-supervised masked image modeling has shown promising results on natural images. However, directly applying such methods to medical images remains challenging. This difficulty stems from the complexity and distinct characteristics of lesions compared to natural images, which impedes effective representation learning. Additionally, conventional high fixed masking ratios restrict reconstructing fine lesion details, limiting the scope of learnable information. To tackle these limitations, we propose a novel self-supervised medical image segmentation framework, Adaptive Masking Lesion Patches (AMLP). Specifically, we design a Masked Patch Selection (MPS) strategy to identify and focus learning on patches containing lesions. Lesion regions are scarce yet critical, making their precise reconstruction vital. To reduce misclassification of lesion and background patches caused by unsupervised clustering in MPS, we introduce an Attention Reconstruction Loss (ARL) to focus on hard-to-reconstruct patches likely depicting lesions. We further propose a Category Consistency Loss (CCL) to refine patch categorization based on reconstruction difficulty, strengthening distinction between lesions and background. Moreover, we develop an Adaptive Masking Ratio (AMR) strategy that gradually increases the masking ratio to expand reconstructible information and improve learning. Extensive experiments on two medical segmentation datasets demonstrate AMLP's superior performance compared to existing self-supervised approaches. The proposed strategies effectively address limitations in applying masked modeling to medical images, tailored to capturing fine lesion details vital for segmentation tasks.

Abstract: License Plate Recognition (LPR) plays a critical role in various applications, such as toll collection, parking management, and traffic law enforcement. Although LPR has witnessed significant advancements through the development of deep learning, there has been a noticeable lack of studies exploring the potential improvements in results by fusing the outputs from multiple recognition models. This research aims to fill this gap by investigating the combination of up to 12 different models using straightforward approaches, such as selecting the most confident prediction or employing majority vote-based strategies. Our experiments encompass a wide range of datasets, revealing substantial benefits of fusion approaches in both intra- and cross-dataset setups. Essentially, fusing multiple models reduces considerably the likelihood of obtaining subpar performance on a particular dataset/scenario. We also found that combining models based on their speed is an appealing approach. Specifically, for applications where the recognition task can tolerate some additional time, though not excessively, an effective strategy is to combine 4-6 models. These models may not be the most accurate individually, but their fusion strikes an optimal balance between accuracy and speed.

Abstract: Sparse Mixture-of-Experts models (MoEs) have recently gained popularity due to their ability to decouple model size from inference efficiency by only activating a small subset of the model parameters for any given input token. As such, sparse MoEs have enabled unprecedented scalability, resulting in tremendous successes across domains such as natural language processing and computer vision. In this work, we instead explore the use of sparse MoEs to scale-down Vision Transformers (ViTs) to make them more attractive for resource-constrained vision applications. To this end, we propose a simplified and mobile-friendly MoE design where entire images rather than individual patches are routed to the experts. We also propose a stable MoE training procedure that uses super-class information to guide the router. We empirically show that our sparse Mobile Vision MoEs (V-MoEs) can achieve a better trade-off between performance and efficiency than the corresponding dense ViTs. For example, for the ViT-Tiny model, our Mobile V-MoE outperforms its dense counterpart by 3.39% on ImageNet-1k. For an even smaller ViT variant with only 54M FLOPs inference cost, our MoE achieves an improvement of 4.66%.

Abstract: We propose a simple yet effective metric that measures structural similarity between visual instances of architectural floor plans, without the need for learning. Qualitatively, our experiments show that the retrieval results are similar to deeply learned methods. Effectively comparing instances of floor plan data is paramount to the success of machine understanding of floor plan data, including the assessment of floor plan generative models and floor plan recommendation systems. Comparing visual floor plan images goes beyond a sole pixel-wise visual examination and is crucially about similarities and differences in the shapes and relations between subdivisions that compose the layout. Currently, deep metric learning approaches are used to learn a pair-wise vector representation space that closely mimics the structural similarity, in which the models are trained on similarity labels that are obtained by Intersection-over-Union (IoU). To compensate for the lack of structural awareness in IoU, graph-based approaches such as Graph Matching Networks (GMNs) are used, which require pairwise inference for comparing data instances, making GMNs less practical for retrieval applications. In this paper, an effective evaluation metric for judging the structural similarity of floor plans, coined SSIG (Structural Similarity by IoU and GED), is proposed based on both image and graph distances. In addition, an efficient algorithm is developed that uses SSIG to rank a large-scale floor plan database. Code will be openly available.

Abstract: Capturing images with incorrect exposure settings fails to deliver a satisfactory visual experience. Only when the exposure is properly set, can the color and details of the images be appropriately preserved. Previous exposure correction methods based on convolutions often produce exposure deviation in images as a consequence of the restricted receptive field of convolutional kernels. This issue arises because convolutions are not capable of capturing long-range dependencies in images accurately. To overcome this challenge, we can apply the Transformer to address the exposure correction problem, leveraging its capability in modeling long-range dependencies to capture global representation. However, solely relying on the window-based Transformer leads to visually disturbing blocking artifacts due to the application of self-attention in small patches. In this paper, we propose a CNN Injected Transformer (CIT) to harness the individual strengths of CNN and Transformer simultaneously. Specifically, we construct the CIT by utilizing a window-based Transformer to exploit the long-range interactions among different regions in the entire image. Within each CIT block, we incorporate a channel attention block (CAB) and a half-instance normalization block (HINB) to assist the window-based self-attention to acquire the global statistics and refine local features. In addition to the hybrid architecture design for exposure correction, we apply a set of carefully formulated loss functions to improve the spatial coherence and rectify potential color deviations. Extensive experiments demonstrate that our image exposure correction method outperforms state-of-the-art approaches in terms of both quantitative and qualitative metrics.

Abstract: Diffusion-model-based text-guided image generation has recently made astounding progress, producing fascinating results in open-domain image manipulation tasks. Few models, however, currently have complete zero-shot capabilities for both global and local image editing due to the complexity and diversity of image manipulation tasks. In this work, we propose a method with a mixture-of-expert (MOE) controllers to align the text-guided capacity of diffusion models with different kinds of human instructions, enabling our model to handle various open-domain image manipulation tasks with natural language instructions. First, we use large language models (ChatGPT) and conditional image synthesis models (ControlNet) to generate a large number of global image transfer dataset in addition to the instruction-based local image editing dataset. Then, using an MOE technique and task-specific adaptation training on a large-scale dataset, our conditional diffusion model can edit images globally and locally. Extensive experiments demonstrate that our approach performs surprisingly well on various image manipulation tasks when dealing with open-domain images and arbitrary human instructions. Please refer to our project page: [https://oppo-mente-lab.github.io/moe_controller/]

Abstract: A new trend in the computer vision community is to capture objects of interest following flexible human command represented by a natural language prompt. However, the progress of using language prompts in driving scenarios is stuck in a bottleneck due to the scarcity of paired prompt-instance data. To address this challenge, we propose the first object-centric language prompt set for driving scenes within 3D, multi-view, and multi-frame space, named NuPrompt. It expands Nuscenes dataset by constructing a total of 35,367 language descriptions, each referring to an average of 5.3 object tracks. Based on the object-text pairs from the new benchmark, we formulate a new prompt-based driving task, \ie, employing a language prompt to predict the described object trajectory across views and frames. Furthermore, we provide a simple end-to-end baseline model based on Transformer, named PromptTrack. Experiments show that our PromptTrack achieves impressive performance on NuPrompt. We hope this work can provide more new insights for the autonomous driving community. Dataset and Code will be made public at \href{https://github.com/wudongming97/Prompt4Driving}{https://github.com/wudongming97/Prompt4Driving}.

Abstract: Recent advancements in diffusion models have showcased their impressive capacity to generate visually striking images. Nevertheless, ensuring a close match between the generated image and the given prompt remains a persistent challenge. In this work, we identify that a crucial factor leading to the text-image mismatch issue is the inadequate cross-modality relation learning between the prompt and the output image. To better align the prompt and image content, we advance the cross-attention with an adaptive mask, which is conditioned on the attention maps and the prompt embeddings, to dynamically adjust the contribution of each text token to the image features. This mechanism explicitly diminishes the ambiguity in semantic information embedding from the text encoder, leading to a boost of text-to-image consistency in the synthesized images. Our method, termed MaskDiffusion, is training-free and hot-pluggable for popular pre-trained diffusion models. When applied to the latent diffusion models, our MaskDiffusion can significantly improve the text-to-image consistency with negligible computation overhead compared to the original diffusion models.

Abstract: In this paper, we address the challenging problem of 3D toonification, which involves transferring the style of an artistic domain onto a target 3D face with stylized geometry and texture. Although fine-tuning a pre-trained 3D GAN on the artistic domain can produce reasonable performance, this strategy has limitations in the 3D domain. In particular, fine-tuning can deteriorate the original GAN latent space, which affects subsequent semantic editing, and requires independent optimization and storage for each new style, limiting flexibility and efficient deployment. To overcome these challenges, we propose DeformToon3D, an effective toonification framework tailored for hierarchical 3D GAN. Our approach decomposes 3D toonification into subproblems of geometry and texture stylization to better preserve the original latent space. Specifically, we devise a novel StyleField that predicts conditional 3D deformation to align a real-space NeRF to the style space for geometry stylization. Thanks to the StyleField formulation, which already handles geometry stylization well, texture stylization can be achieved conveniently via adaptive style mixing that injects information of the artistic domain into the decoder of the pre-trained 3D GAN. Due to the unique design, our method enables flexible style degree control and shape-texture-specific style swap. Furthermore, we achieve efficient training without any real-world 2D-3D training pairs but proxy samples synthesized from off-the-shelf 2D toonification models.

Abstract: Creating a diverse and comprehensive dataset of hand gestures for dynamic human-machine interfaces in the automotive domain can be challenging and time-consuming. To overcome this challenge, we propose using synthetic gesture datasets generated by virtual 3D models. Our framework utilizes Unreal Engine to synthesize realistic hand gestures, offering customization options and reducing the risk of overfitting. Multiple variants, including gesture speed, performance, and hand shape, are generated to improve generalizability. In addition, we simulate different camera locations and types, such as RGB, infrared, and depth cameras, without incurring additional time and cost to obtain these cameras. Experimental results demonstrate that our proposed framework, SynthoGestures\footnote{\url{https://github.com/amrgomaaelhady/SynthoGestures}}, improves gesture recognition accuracy and can replace or augment real-hand datasets. By saving time and effort in the creation of the data set, our tool accelerates the development of gesture recognition systems for automotive applications.

Abstract: Performing multiple heterogeneous visual tasks in dynamic scenes is a hallmark of human perception capability. Despite remarkable progress in image and video recognition via representation learning, current research still focuses on designing specialized networks for singular, homogeneous, or simple combination of tasks. We instead explore the construction of a unified model for major image and video recognition tasks in autonomous driving with diverse input and output structures. To enable such an investigation, we design a new challenge, Video Task Decathlon (VTD), which includes ten representative image and video tasks spanning classification, segmentation, localization, and association of objects and pixels. On VTD, we develop our unified network, VTDNet, that uses a single structure and a single set of weights for all ten tasks. VTDNet groups similar tasks and employs task interaction stages to exchange information within and between task groups. Given the impracticality of labeling all tasks on all frames, and the performance degradation associated with joint training of many tasks, we design a Curriculum training, Pseudo-labeling, and Fine-tuning (CPF) scheme to successfully train VTDNet on all tasks and mitigate performance loss. Armed with CPF, VTDNet significantly outperforms its single-task counterparts on most tasks with only 20% overall computations. VTD is a promising new direction for exploring the unification of perception tasks in autonomous driving.

Abstract: Text-to-image generative models can produce diverse high-quality images of concepts with a text prompt, which have demonstrated excellent ability in image generation, image translation, etc. We in this work study the problem of synthesizing instantiations of a use's own concepts in a never-ending manner, i.e., create your world, where the new concepts from user are quickly learned with a few examples. To achieve this goal, we propose a Lifelong text-to-image Diffusion Model (L2DM), which intends to overcome knowledge "catastrophic forgetting" for the past encountered concepts, and semantic "catastrophic neglecting" for one or more concepts in the text prompt. In respect of knowledge "catastrophic forgetting", our L2DM framework devises a task-aware memory enhancement module and a elastic-concept distillation module, which could respectively safeguard the knowledge of both prior concepts and each past personalized concept. When generating images with a user text prompt, the solution to semantic "catastrophic neglecting" is that a concept attention artist module can alleviate the semantic neglecting from concept aspect, and an orthogonal attention module can reduce the semantic binding from attribute aspect. To the end, our model can generate more faithful image across a range of continual text prompts in terms of both qualitative and quantitative metrics, when comparing with the related state-of-the-art models. The code will be released at https://wenqiliang.github.io/.

Abstract: Refractive Index Tomography is an inverse problem in which we seek to reconstruct a scene's 3D refractive field from 2D projected image measurements. The refractive field is not visible itself, but instead affects how the path of a light ray is continuously curved as it travels through space. Refractive fields appear across a wide variety of scientific applications, from translucent cell samples in microscopy to fields of dark matter bending light from faraway galaxies. This problem poses a unique challenge because the refractive field directly affects the path that light takes, making its recovery a non-linear problem. In addition, in contrast with traditional tomography, we seek to recover the refractive field using a projected image from only a single viewpoint by leveraging knowledge of light sources scattered throughout the medium. In this work, we introduce a method that uses a coordinate-based neural network to model the underlying continuous refractive field in a scene. We then use explicit modeling of rays' 3D spatial curvature to optimize the parameters of this network, reconstructing refractive fields with an analysis-by-synthesis approach. The efficacy of our approach is demonstrated by recovering refractive fields in simulation, and analyzing how recovery is affected by the light source distribution. We then test our method on a simulated dark matter mapping problem, where we recover the refractive field underlying a realistic simulated dark matter distribution.

Abstract: Most studies to date that have examined demographic variations in face recognition accuracy have analyzed 1-to-1 matching accuracy, using images that could be described as "government ID quality". This paper analyzes the accuracy of 1-to-many facial identification across demographic groups, and in the presence of blur and reduced resolution in the probe image as might occur in "surveillance camera quality" images. Cumulative match characteristic curves(CMC) are not appropriate for comparing propensity for rank-one recognition errors across demographics, and so we introduce three metrics for this: (1) d' metric between mated and non-mated score distributions, (2) absolute score difference between thresholds in the high-similarity tail of the non-mated and the low-similarity tail of the mated distribution, and (3) distribution of (mated - non-mated rank one scores) across the set of probe images. We find that demographic variation in 1-to-many accuracy does not entirely follow what has been observed in 1-to-1 matching accuracy. Also, different from 1-to-1 accuracy, demographic comparison of 1-to-many accuracy can be affected by different numbers of identities and images across demographics. Finally, we show that increased blur in the probe image, or reduced resolution of the face in the probe image, can significantly increase the false positive identification rate. And we show that the demographic variation in these high blur or low resolution conditions is much larger for male/ female than for African-American / Caucasian. The point that 1-to-many accuracy can potentially collapse in the context of processing "surveillance camera quality" probe images against a "government ID quality" gallery is an important one.

Abstract: Sensor-equipped unoccupied aerial vehicles (UAVs) have the potential to help reduce search times and alleviate safety risks for first responders carrying out Wilderness Search and Rescue (WiSAR) operations, the process of finding and rescuing person(s) lost in wilderness areas. Unfortunately, visual sensors alone do not address the need for robustness across all the possible terrains, weather, and lighting conditions that WiSAR operations can be conducted in. The use of multi-modal sensors, specifically visual-thermal cameras, is critical in enabling WiSAR UAVs to perform in diverse operating conditions. However, due to the unique challenges posed by the wilderness context, existing dataset benchmarks are inadequate for developing vision-based algorithms for autonomous WiSAR UAVs. To this end, we present WiSARD, a dataset with roughly 56,000 labeled visual and thermal images collected from UAV flights in various terrains, seasons, weather, and lighting conditions. To the best of our knowledge, WiSARD is the first large-scale dataset collected with multi-modal sensors for autonomous WiSAR operations. We envision that our dataset will provide researchers with a diverse and challenging benchmark that can test the robustness of their algorithms when applied to real-world (life-saving) applications.

Abstract: Real-world application of chest X-ray abnormality classification requires dealing with several challenges: (i) limited training data; (ii) training and evaluation sets that are derived from different domains; and (iii) classes that appear during training may have partial overlap with classes of interest during evaluation. To address these challenges, we present an integrated framework called Generalized Cross-Domain Multi-Label Few-Shot Learning (GenCDML-FSL). The framework supports overlap in classes during training and evaluation, cross-domain transfer, adopts meta-learning to learn using few training samples, and assumes each chest X-ray image is either normal or associated with one or more abnormalities. Furthermore, we propose Generalized Episodic Training (GenET), a training strategy that equips models to operate with multiple challenges observed in the GenCDML-FSL scenario. Comparisons with well-established methods such as transfer learning, hybrid transfer learning, and multi-label meta-learning on multiple datasets show the superiority of our approach.