Adversarial attacks exploit vulnerabilities in a model's decision boundaries through small, carefully crafted perturbations that lead to significant mispredictions. In 3D vision, the high dimensionality and sparsity of data greatly expand the attack surface, making 3D vision particularly vulnerable for safety-critical robotics. To enhance 3D vision's adversarial robustness, we propose a training objective that simultaneously minimizes prediction loss and mutual information (MI) under adversarial perturbations to contain the upper bound of misprediction errors. This approach simplifies handling adversarial examples compared to conventional methods, which require explicit searching and training on adversarial samples. However, minimizing prediction loss conflicts with minimizing MI, leading to reduced robustness and catastrophic forgetting. To address this, we integrate curriculum advisors in the training setup that gradually introduce adversarial objectives to balance training and prevent models from being overwhelmed by difficult cases early in the process. The advisors also enhance robustness by encouraging training on diverse MI examples through entropy regularizers. We evaluated our method on ModelNet40 and KITTI using PointNet, DGCNN, SECOND, and PointTransformers, achieving 2-5% accuracy gains on ModelNet40 and a 5-10% mAP improvement in object detection. Our code is publicly available at https://github.com/nstrndrbi/Mine-N-Learn.
This work addresses the challenge of adapting dynamic deadline requirements for LiDAR object detection deep neural networks (DNNs). The computing latency of object detection is critically important to ensure safe and efficient navigation. However, state-of-the-art LiDAR object detection DNNs often exhibit significant latency, hindering their real-time performance on resource-constrained edge platforms. Therefore, a tradeoff between detection accuracy and latency should be dynamically managed at runtime to achieve optimum results. In this paper, we introduce VALO (Versatile Anytime algorithm for LiDAR Object detection), a novel data-centric approach that enables anytime computing of 3D LiDAR object detection DNNs. VALO employs a deadline-aware scheduler to selectively process input regions, making execution time and accuracy tradeoffs without architectural modifications. Additionally, it leverages efficient forecasting of past detection results to mitigate possible loss of accuracy due to partial processing of input. Finally, it utilizes a novel input reduction technique within its detection heads to significantly accelerate execution without sacrificing accuracy. We implement VALO on state-of-the-art 3D LiDAR object detection networks, namely CenterPoint and VoxelNext, and demonstrate its dynamic adaptability to a wide range of time constraints while achieving higher accuracy than the prior state-of-the-art. Code is available athttps://github.com/CSL-KU/VALO}{github.com/CSL-KU/VALO.
With the ever-growing complexity of models in the field of remote sensing (RS), there is an increasing demand for solutions that balance model accuracy with computational efficiency. Knowledge distillation (KD) has emerged as a powerful tool to meet this need, enabling the transfer of knowledge from large, complex models to smaller, more efficient ones without significant loss in performance. This review article provides an extensive examination of KD and its innovative applications in RS. KD, a technique developed to transfer knowledge from a complex, often cumbersome model (teacher) to a more compact and efficient model (student), has seen significant evolution and application across various domains. Initially, we introduce the fundamental concepts and historical progression of KD methods. The advantages of employing KD are highlighted, particularly in terms of model compression, enhanced computational efficiency, and improved performance, which are pivotal for practical deployments in RS scenarios. The article provides a comprehensive taxonomy of KD techniques, where each category is critically analyzed to demonstrate the breadth and depth of the alternative options, and illustrates specific case studies that showcase the practical implementation of KD methods in RS tasks, such as instance segmentation and object detection. Further, the review discusses the challenges and limitations of KD in RS, including practical constraints and prospective future directions, providing a comprehensive overview for researchers and practitioners in the field of RS. Through this organization, the paper not only elucidates the current state of research in KD but also sets the stage for future research opportunities, thereby contributing significantly to both academic research and real-world applications.
We present Agglomerative Token Clustering (ATC), a novel token merging method that consistently outperforms previous token merging and pruning methods across image classification, image synthesis, and object detection & segmentation tasks. ATC merges clusters through bottom-up hierarchical clustering, without the introduction of extra learnable parameters. We find that ATC achieves state-of-the-art performance across all tasks, and can even perform on par with prior state-of-the-art when applied off-the-shelf, i.e. without fine-tuning. ATC is particularly effective when applied with low keep rates, where only a small fraction of tokens are kept and retaining task performance is especially difficult.
3D Multi-Object Tracking (MOT) obtains significant performance improvements with the rapid advancements in 3D object detection, particularly in cost-effective multi-camera setups. However, the prevalent end-to-end training approach for multi-camera trackers results in detector-specific models, limiting their versatility. Moreover, current generic trackers overlook the unique features of multi-camera detectors, i.e., the unreliability of motion observations and the feasibility of visual information. To address these challenges, we propose RockTrack, a 3D MOT method for multi-camera detectors. Following the Tracking-By-Detection framework, RockTrack is compatible with various off-the-shelf detectors. RockTrack incorporates a confidence-guided preprocessing module to extract reliable motion and image observations from distinct representation spaces from a single detector. These observations are then fused in an association module that leverages geometric and appearance cues to minimize mismatches. The resulting matches are propagated through a staged estimation process, forming the basis for heuristic noise modeling. Additionally, we introduce a novel appearance similarity metric for explicitly characterizing object affinities in multi-camera settings. RockTrack achieves state-of-the-art performance on the nuScenes vision-only tracking leaderboard with 59.1% AMOTA while demonstrating impressive computational efficiency.
Occupancy and 3D object detection are characterized as two standard tasks in modern autonomous driving system. In order to deploy them on a series of edge chips with better precision and time-consuming trade-off, contemporary approaches either deploy standalone models for individual tasks, or design a multi-task paradigm with separate heads. However, they might suffer from deployment difficulties (i.e., 3D convolution, transformer and so on) or deficiencies in task coordination. Instead, we argue that a favorable framework should be devised in pursuit of ease deployment on diverse chips and high precision with little time-consuming. Oriented at this, we revisit the paradigm for interaction between 3D object detection and occupancy prediction, reformulate the model with 2D convolution and prioritize the tasks such that each contributes to other. Thus, we propose a method to achieve fast 3D object detection and occupancy prediction (UltimateDO), wherein the light occupancy prediction head in FlashOcc is married to 3D object detection network, with negligible additional timeconsuming of only 1.1ms while facilitating each other. We instantiate UltimateDO on the challenging nuScenes-series benchmarks.
The LiDAR-based 3D object detector that strikes a balance between accuracy and speed is crucial for achieving real-time perception in autonomous driving and robotic navigation systems. To enhance the accuracy of point cloud detection, integrating global context for visual understanding improves the point clouds ability to grasp overall spatial information. However, many existing LiDAR detection models depend on intricate feature transformation and extraction processes, leading to poor real-time performance and high resource consumption, which limits their practical effectiveness. In this work, we propose a Faster LiDAR 3D object detection framework, called FASD, which implements heterogeneous model distillation by adaptively uniform cross-model voxel features. We aim to distill the transformer's capacity for high-performance sequence modeling into Mamba models with low FLOPs, achieving a significant improvement in accuracy through knowledge transfer. Specifically, Dynamic Voxel Group and Adaptive Attention strategies are integrated into the sparse backbone, creating a robust teacher model with scale-adaptive attention for effective global visual context modeling. Following feature alignment with the Adapter, we transfer knowledge from the Transformer to the Mamba through latent space feature supervision and span-head distillation, resulting in improved performance and an efficient student model. We evaluated the framework on the Waymo and nuScenes datasets, achieving a 4x reduction in resource consumption and a 1-2\% performance improvement over the current SoTA methods.
Semi-supervised 3D object detection is a common strategy employed to circumvent the challenge of manually labeling large-scale autonomous driving perception datasets. Pseudo-labeling approaches to semi-supervised learning adopt a teacher-student framework in which machine-generated pseudo-labels on a large unlabeled dataset are used in combination with a small manually-labeled dataset for training. In this work, we address the problem of improving pseudo-label quality through leveraging long-term temporal information captured in driving scenes. More specifically, we leverage pre-trained motion-forecasting models to generate object trajectories on pseudo-labeled data to further enhance the student model training. Our approach improves pseudo-label quality in two distinct manners: first, we suppress false positive pseudo-labels through establishing consistency across multiple frames of motion forecasting outputs. Second, we compensate for false negative detections by directly inserting predicted object tracks into the pseudo-labeled scene. Experiments on the nuScenes dataset demonstrate the effectiveness of our approach, improving the performance of standard semi-supervised approaches in a variety of settings.
This paper presents a novel way of online adapting any off-the-shelf object detection model to a novel domain without retraining the detector model. Inspired by how humans quickly learn knowledge of a new subject (e.g., memorization), we allow the detector to look up similar object concepts from memory during test time. This is achieved through a retrieval augmented classification (RAC) module together with a memory bank that can be flexibly updated with new domain knowledge. We experimented with various off-the-shelf open-set detector and close-set detectors. With only a tiny memory bank (e.g., 10 images per category) and being training-free, our online learning method could significantly outperform baselines in adapting a detector to novel domains.
Cooperative perception systems play a vital role in enhancing the safety and efficiency of vehicular autonomy. Although recent studies have highlighted the efficacy of vehicle-to-everything (V2X) communication techniques in autonomous driving, a significant challenge persists: how to efficiently integrate multiple high-bandwidth features across an expanding network of connected agents such as vehicles and infrastructure. In this paper, we introduce CoMamba, a novel cooperative 3D detection framework designed to leverage state-space models for real-time onboard vehicle perception. Compared to prior state-of-the-art transformer-based models, CoMamba enjoys being a more scalable 3D model using bidirectional state space models, bypassing the quadratic complexity pain-point of attention mechanisms. Through extensive experimentation on V2X/V2V datasets, CoMamba achieves superior performance compared to existing methods while maintaining real-time processing capabilities. The proposed framework not only enhances object detection accuracy but also significantly reduces processing time, making it a promising solution for next-generation cooperative perception systems in intelligent transportation networks.
Multiple object tracking (MOT) in Unmanned Aerial Vehicle (UAV) videos is important for diverse applications in computer vision. Current MOT trackers rely on accurate object detection results and precise matching of target reidentification (ReID). These methods focus on optimizing target spatial attributes while overlooking temporal cues in modelling object relationships, especially for challenging tracking conditions such as object deformation and blurring, etc. To address the above-mentioned issues, we propose a novel Spatio-Temporal Cohesion Multiple Object Tracking framework (STCMOT), which utilizes historical embedding features to model the representation of ReID and detection features in a sequential order. Concretely, a temporal embedding boosting module is introduced to enhance the discriminability of individual embedding based on adjacent frame cooperation. While the trajectory embedding is then propagated by a temporal detection refinement module to mine salient target locations in the temporal field. Extensive experiments on the VisDrone2019 and UAVDT datasets demonstrate our STCMOT sets a new state-of-the-art performance in MOTA and IDF1 metrics. The source codes are released at https://github.com/ydhcg-BoBo/STCMOT.
Most instance perception and image understanding solutions focus mainly on natural images. However, applications for synthetic images, and more specifically, images of Graphical User Interfaces (GUI) remain limited. This hinders the development of autonomous computer-vision-powered Artificial Intelligence (AI) agents. In this work, we present Instruction Visual Grounding or IVG, a multi-modal solution for object identification in a GUI. More precisely, given a natural language instruction and GUI screen, IVG locates the coordinates of the element on the screen where the instruction would be executed. To this end, we develop two methods. The first method is a three-part architecture that relies on a combination of a Large Language Model (LLM) and an object detection model. The second approach uses a multi-modal foundation model.
The training of deep and/or convolutional neural networks (DNNs/CNNs) is traditionally done on servers with powerful CPUs and GPUs. Recent efforts have emerged to localize machine learning tasks fully on the edge. This brings advantages in reduced latency and increased privacy, but necessitates working with resource-constrained devices. Approaches for inference and training in mobile and edge devices based on pruning, quantization or incremental and transfer learning require trading off accuracy. Several works have explored distributing inference operations on mobile and edge clusters instead. However, there is limited literature on distributed training on the edge. Existing approaches all require a central, potentially powerful edge or cloud server for coordination or offloading. In this paper, we describe an approach for distributed CNN training exclusively on mobile and edge devices. Our approach is beneficial for the initial CNN layers that are feature map dominated. It is based on partitioning forward inference and back-propagation operations among devices through tiling and fusing to maximize locality and expose communication and memory-aware parallelism. We also introduce the concept of layer grouping to further fine-tune performance based on computation and communication trade-off. Results show that for a cluster of 2-6 quad-core Raspberry Pi3 devices, training of an object-detection CNN provides a 2x-15x speedup with respect to a single core and up to 8x reduction in memory usage per device, all without sacrificing accuracy. Grouping offers up to 1.5x speedup depending on the reference profile and batch size.
Object detection has achieved remarkable advancements through the utilization of deep neural networks; however, its heavy reliance on extensive labeled data remains a significant challenge. We first delve into active learning strategies that leverage the power of uncertainty estimation and detector resilience. Departing from approaches biased toward high performing classes, we present an innovative solution known as Hierarchical Uncertainty Aggregation and Emphasis Loss (HUALE). This approach introduces hierarchical uncertainty aggregation, which effectively retrieves and ranks unlabeled images for precise image selection. Secondly, we introduce the Emphasis loss, a novel loss augmentation to object detection training and combine it with the EIoU loss and Synchronic IoU-Localization loss to elevate the accuracy of bounding box localization and address non-convexity challenges. Our method, built upon the Faster R-CNN framework, consistently outperforms the baseline (random selection) with average mAP (%) improvements of 4.53/3.44/1.57 across the PASCAL VOC 2007, PASCAL VOC 2012, and MS COCO datasets.
Vision-language models have recently evolved into versatile systems capable of high performance across a range of tasks, such as document understanding, visual question answering, and grounding, often in zero-shot settings. Comics Understanding, a complex and multifaceted field, stands to greatly benefit from these advances. Comics, as a medium, combine rich visual and textual narratives, challenging AI models with tasks that span image classification, object detection, instance segmentation, and deeper narrative comprehension through sequential panels. However, the unique structure of comics -- characterized by creative variations in style, reading order, and non-linear storytelling -- presents a set of challenges distinct from those in other visual-language domains. In this survey, we present a comprehensive review of Comics Understanding from both dataset and task perspectives. Our contributions are fivefold: (1) We analyze the structure of the comics medium, detailing its distinctive compositional elements; (2) We survey the widely used datasets and tasks in comics research, emphasizing their role in advancing the field; (3) We introduce the Layer of Comics Understanding (LoCU) framework, a novel taxonomy that redefines vision-language tasks within comics and lays the foundation for future work; (4) We provide a detailed review and categorization of existing methods following the LoCU framework; (5) Finally, we highlight current research challenges and propose directions for future exploration, particularly in the context of vision-language models applied to comics. This survey is the first to propose a task-oriented framework for comics intelligence and aims to guide future research by addressing critical gaps in data availability and task definition. A project associated with this survey is available at https://github.com/emanuelevivoli/awesome-comics-understanding.
This study introduces a laboratory experiment designed to assess the influence of annotation strategies, levels of imbalanced data, and prior experience, on the performance of human annotators. The experiment focuses on labeling aerial imagery, using ArcGIS Pro tools, to detect and segment small-scale photovoltaic solar panels, selected as a case study for rectangular objects. The experiment is conducted using images with a pixel size of 0.15\textbf{$m$}, involving both expert and non-expert participants, across different setup strategies and target-background ratio datasets. Our findings indicate that human annotators generally perform more effectively in object detection than in segmentation tasks. A marked tendency to commit more Type II errors (False Negatives, i.e., undetected objects) than Type I errors (False Positives, i.e. falsely detecting objects that do not exist) was observed across all experimental setups and conditions, suggesting a consistent bias in detection and segmentation processes. Performance was better in tasks with higher target-background ratios (i.e., more objects per unit area). Prior experience did not significantly impact performance and may, in some cases, even lead to overestimation in segmentation. These results provide evidence that human annotators are relatively cautious and tend to identify objects only when they are confident about them, prioritizing underestimation over overestimation. Annotators' performance is also influenced by object scarcity, showing a decline in areas with extremely imbalanced datasets and a low ratio of target-to-background. These findings may enhance annotation strategies for remote sensing research while efficient human annotators are crucial in an era characterized by growing demands for high-quality training data to improve segmentation and detection models.
The recent emergence of Distributed Acoustic Sensing (DAS) technology has facilitated the effective capture of traffic-induced seismic data. The traffic-induced seismic wave is a prominent contributor to urban vibrations and contain crucial information to advance urban exploration and governance. However, identifying vehicular movements within massive noisy data poses a significant challenge. In this study, we introduce a real-time semi-supervised vehicle monitoring framework tailored to urban settings. It requires only a small fraction of manual labels for initial training and exploits unlabeled data for model improvement. Additionally, the framework can autonomously adapt to newly collected unlabeled data. Before DAS data undergo object detection as two-dimensional images to preserve spatial information, we leveraged comprehensive one-dimensional signal preprocessing to mitigate noise. Furthermore, we propose a novel prior loss that incorporates the shapes of vehicular traces to track a single vehicle with varying speeds. To evaluate our model, we conducted experiments with seismic data from the Stanford 2 DAS Array. The results showed that our model outperformed the baseline model Efficient Teacher and its supervised counterpart, YOLO (You Only Look Once), in both accuracy and robustness. With only 35 labeled images, our model surpassed YOLO's mAP 0.5:0.95 criterion by 18% and showed a 7% increase over Efficient Teacher. We conducted comparative experiments with multiple update strategies for self-updating and identified an optimal approach. This approach surpasses the performance of non-overfitting training conducted with all data in a single pass.
The significant advancements in embodied vision navigation have raised concerns about its susceptibility to adversarial attacks exploiting deep neural networks. Investigating the adversarial robustness of embodied vision navigation is crucial, especially given the threat of 3D physical attacks that could pose risks to human safety. However, existing attack methods for embodied vision navigation often lack physical feasibility due to challenges in transferring digital perturbations into the physical world. Moreover, current physical attacks for object detection struggle to achieve both multi-view effectiveness and visual naturalness in navigation scenarios. To address this, we propose a practical attack method for embodied navigation by attaching adversarial patches to objects, where both opacity and textures are learnable. Specifically, to ensure effectiveness across varying viewpoints, we employ a multi-view optimization strategy based on object-aware sampling, which optimizes the patch's texture based on feedback from the vision-based perception model used in navigation. To make the patch inconspicuous to human observers, we introduce a two-stage opacity optimization mechanism, in which opacity is fine-tuned after texture optimization. Experimental results demonstrate that our adversarial patches decrease the navigation success rate by an average of 22.39%, outperforming previous methods in practicality, effectiveness, and naturalness. Code is available at: https://github.com/chen37058/Physical-Attacks-in-Embodied-Nav
Recent advances in VLSI fabrication technology have led to die shrinkage and increased layout density, creating an urgent demand for advanced hotspot detection techniques. However, by taking an object detection network as the backbone, recent learning-based hotspot detectors learn to recognize only the problematic layout patterns in the training data. This fact makes these hotspot detectors difficult to generalize to real-world scenarios. We propose a novel lithography simulator-powered hotspot detection framework to overcome this difficulty. Our framework integrates a lithography simulator with an object detection backbone, merging the extracted latent features from both the simulator and the object detector via well-designed cross-attention blocks. Consequently, the proposed framework can be used to detect potential hotspot regions based on I) the variation of possible circuit shape deformation estimated by the lithography simulator, and ii) the problematic layout patterns already known. To this end, we utilize RetinaNet with a feature pyramid network as the object detection backbone and leverage LithoNet as the lithography simulator. Extensive experiments demonstrate that our proposed simulator-guided hotspot detection framework outperforms previous state-of-the-art methods on real-world data.
In recent years, workplaces and educational institutes have widely adopted virtual meeting platforms. This has led to a growing interest in analyzing and extracting insights from these meetings, which requires effective detection and tracking of unique individuals. In practice, there is no standardization in video meetings recording layout, and how they are captured across the different platforms and services. This, in turn, creates a challenge in acquiring this data stream and analyzing it in a uniform fashion. Our approach provides a solution to the most general form of video recording, usually consisting of a grid of participants (\cref{fig:videomeeting}) from a single video source with no metadata on participant locations, while using the least amount of constraints and assumptions as to how the data was acquired. Conventional approaches often use YOLO models coupled with tracking algorithms, assuming linear motion trajectories akin to that observed in CCTV footage. However, such assumptions fall short in virtual meetings, where participant video feed window can abruptly change location across the grid. In an organic video meeting setting, participants frequently join and leave, leading to sudden, non-linear movements on the video grid. This disrupts optical flow-based tracking methods that depend on linear motion. Consequently, standard object detection and tracking methods might mistakenly assign multiple participants to the same tracker. In this paper, we introduce a novel approach to track and re-identify participants in remote video meetings, by utilizing the spatio-temporal priors arising from the data in our domain. This, in turn, increases tracking capabilities compared to the use of general object tracking. Our approach reduces the error rate by 95% on average compared to YOLO-based tracking methods as a baseline.