Abstract:Transformers are widely used in computer vision areas and have achieved remarkable success. Most state-of-the-art approaches split images into regular grids and represent each grid region with a vision token. However, fixed token distribution disregards the semantic meaning of different image regions, resulting in sub-optimal performance. To address this issue, we propose the Token Clustering Transformer (TCFormer), which generates dynamic vision tokens based on semantic meaning. Our dynamic tokens possess two crucial characteristics: (1) Representing image regions with similar semantic meanings using the same vision token, even if those regions are not adjacent, and (2) concentrating on regions with valuable details and represent them using fine tokens. Through extensive experimentation across various applications, including image classification, human pose estimation, semantic segmentation, and object detection, we demonstrate the effectiveness of our TCFormer. The code and models for this work are available at https://github.com/zengwang430521/TCFormer.
Abstract:Recent years have witnessed increasing research attention towards pedestrian detection by taking the advantages of different sensor modalities (e.g. RGB, IR, Depth, LiDAR and Event). However, designing a unified generalist model that can effectively process diverse sensor modalities remains a challenge. This paper introduces MMPedestron, a novel generalist model for multimodal perception. Unlike previous specialist models that only process one or a pair of specific modality inputs, MMPedestron is able to process multiple modal inputs and their dynamic combinations. The proposed approach comprises a unified encoder for modal representation and fusion and a general head for pedestrian detection. We introduce two extra learnable tokens, i.e. MAA and MAF, for adaptive multi-modal feature fusion. In addition, we construct the MMPD dataset, the first large-scale benchmark for multi-modal pedestrian detection. This benchmark incorporates existing public datasets and a newly collected dataset called EventPed, covering a wide range of sensor modalities including RGB, IR, Depth, LiDAR, and Event data. With multi-modal joint training, our model achieves state-of-the-art performance on a wide range of pedestrian detection benchmarks, surpassing leading models tailored for specific sensor modality. For example, it achieves 71.1 AP on COCO-Persons and 72.6 AP on LLVIP. Notably, our model achieves comparable performance to the InternImage-H model on CrowdHuman with 30x smaller parameters. Codes and data are available at https://github.com/BubblyYi/MMPedestron.
Abstract:Endowing Large Multimodal Models (LMMs) with visual grounding capability can significantly enhance AIs' understanding of the visual world and their interaction with humans. However, existing methods typically fine-tune the parameters of LMMs to learn additional segmentation tokens and overfit grounding and segmentation datasets. Such a design would inevitably cause a catastrophic diminution in the indispensable conversational capability of general AI assistants. In this paper, we comprehensively evaluate state-of-the-art grounding LMMs across a suite of multimodal question-answering benchmarks, observing pronounced performance drops that indicate vanishing general knowledge comprehension and weakened instruction following ability. To address this issue, we present F-LMM -- grounding frozen off-the-shelf LMMs in human-AI conversations -- a straightforward yet effective design based on the fact that word-pixel correspondences conducive to visual grounding inherently exist in the attention weights of well-trained LMMs. Using only a few trainable CNN layers, we can translate word-pixel attention weights to mask logits, which a SAM-based mask refiner can further optimise. Our F-LMM neither learns special segmentation tokens nor utilises high-quality grounded instruction-tuning data, but achieves competitive performance on referring expression segmentation and panoptic narrative grounding benchmarks while completely preserving LMMs' original conversational ability. Additionally, with instruction-following ability preserved and grounding ability obtained, our F-LMM can perform visual chain-of-thought reasoning and better resist object hallucinations.
Abstract:Lensless cameras, innovatively replacing traditional lenses for ultra-thin, flat optics, encode light directly onto sensors, producing images that are not immediately recognizable. This compact, lightweight, and cost-effective imaging solution offers inherent privacy advantages, making it attractive for privacy-sensitive applications like face verification. Typical lensless face verification adopts a two-stage process of reconstruction followed by verification, incurring privacy risks from reconstructed faces and high computational costs. This paper presents an end-to-end optimization approach for privacy-preserving face verification directly on encoded lensless captures, ensuring that the entire software pipeline remains encoded with no visible faces as intermediate results. To achieve this, we propose several techniques to address unique challenges from the lensless setup which precludes traditional face detection and alignment. Specifically, we propose a face center alignment scheme, an augmentation curriculum to build robustness against variations, and a knowledge distillation method to smooth optimization and enhance performance. Evaluations under both simulation and real environment demonstrate our method outperforms two-stage lensless verification while enhancing privacy and efficiency. Project website: \url{lenslessface.github.io}.
Abstract:In the realm of autonomous driving, robust perception under out-of-distribution conditions is paramount for the safe deployment of vehicles. Challenges such as adverse weather, sensor malfunctions, and environmental unpredictability can severely impact the performance of autonomous systems. The 2024 RoboDrive Challenge was crafted to propel the development of driving perception technologies that can withstand and adapt to these real-world variabilities. Focusing on four pivotal tasks -- BEV detection, map segmentation, semantic occupancy prediction, and multi-view depth estimation -- the competition laid down a gauntlet to innovate and enhance system resilience against typical and atypical disturbances. This year's challenge consisted of five distinct tracks and attracted 140 registered teams from 93 institutes across 11 countries, resulting in nearly one thousand submissions evaluated through our servers. The competition culminated in 15 top-performing solutions, which introduced a range of innovative approaches including advanced data augmentation, multi-sensor fusion, self-supervised learning for error correction, and new algorithmic strategies to enhance sensor robustness. These contributions significantly advanced the state of the art, particularly in handling sensor inconsistencies and environmental variability. Participants, through collaborative efforts, pushed the boundaries of current technologies, showcasing their potential in real-world scenarios. Extensive evaluations and analyses provided insights into the effectiveness of these solutions, highlighting key trends and successful strategies for improving the resilience of driving perception systems. This challenge has set a new benchmark in the field, providing a rich repository of techniques expected to guide future research in this field.
Abstract:Instance perception tasks (object detection, instance segmentation, pose estimation, counting) play a key role in industrial applications of visual models. As supervised learning methods suffer from high labeling cost, few-shot learning methods which effectively learn from a limited number of labeled examples are desired. Existing few-shot learning methods primarily focus on a restricted set of tasks, presumably due to the challenges involved in designing a generic model capable of representing diverse tasks in a unified manner. In this paper, we propose UniFS, a universal few-shot instance perception model that unifies a wide range of instance perception tasks by reformulating them into a dynamic point representation learning framework. Additionally, we propose Structure-Aware Point Learning (SAPL) to exploit the higher-order structural relationship among points to further enhance representation learning. Our approach makes minimal assumptions about the tasks, yet it achieves competitive results compared to highly specialized and well optimized specialist models. Codes will be released soon.
Abstract:Autonomous robots in endovascular interventions possess the potential to navigate guidewires with safety and reliability, while reducing human error and shortening surgical time. However, current methods of guidewire navigation based on Reinforcement Learning (RL) depend on manual demonstration data or magnetic guidance. In this work, we propose an Image-guided Autonomous Guidewire Navigation (IAGN) method. Specifically, we introduce BDA-star, a path planning algorithm with boundary distance constraints, for the trajectory planning of guidewire navigation. We established an IAGN-RL environment where the observations are real-time guidewire feeding images highlighting the position of the guidewire tip and the planned path. We proposed a reward function based on the distances from both the guidewire tip to the planned path and the target to evaluate the agent's actions. Furthermore, in policy network, we employ a pre-trained convolutional neural network to extract features, mitigating stability issues and slow convergence rates associated with direct learning from raw pixels. Experiments conducted on the aortic simulation IAGN platform demonstrated that the proposed method, targeting the left subclavian artery and the brachiocephalic artery, achieved a 100% guidewire navigation success rate, along with reduced movement and retraction distances and trajectories tend to the center of the vessels.
Abstract:The rigid registration of aortic Digital Subtraction Angiography (DSA) and Computed Tomography Angiography (CTA) can provide 3D anatomical details of the vasculature for the interventional surgical treatment of conditions such as aortic dissection and aortic aneurysms, holding significant value for clinical research. However, the current methods for 2D/3D image registration are dependent on manual annotations or synthetic data, as well as the extraction of landmarks, which is not suitable for cross-modal registration of aortic DSA/CTA. In this paper, we propose an unsupervised method, UDCR, for aortic DSA/CTA rigid registration based on deep reinforcement learning. Leveraging the imaging principles and characteristics of DSA and CTA, we have constructed a cross-dimensional registration environment based on spatial transformations. Specifically, we propose an overlap degree calculation reward function that measures the intensity difference between the foreground and background, aimed at assessing the accuracy of registration between segmentation maps and DSA images. This method is highly flexible, allowing for the loading of pre-trained models to perform registration directly or to seek the optimal spatial transformation parameters through online learning. We manually annotated 61 pairs of aortic DSA/CTA for algorithm evaluation. The results indicate that the proposed UDCR achieved a Mean Absolute Error (MAE) of 2.85 mm in translation and 4.35{\deg} in rotation, showing significant potential for clinical applications.
Abstract:Motion synthesis in real-world 3D scenes has recently attracted much attention. However, the static environment assumption made by most current methods usually cannot be satisfied especially for real-time motion synthesis in scanned point cloud scenes, if multiple dynamic objects exist, e.g., moving persons or vehicles. To handle this problem, we propose the first Dynamic Environment MOtion Synthesis framework (DEMOS) to predict future motion instantly according to the current scene, and use it to dynamically update the latent motion for final motion synthesis. Concretely, we propose a Spherical-BEV perception method to extract local scene features that are specifically designed for instant scene-aware motion prediction. Then, we design a time-variant motion blending to fuse the new predicted motions into the latent motion, and the final motion is derived from the updated latent motions, benefitting both from motion-prior and iterative methods. We unify the data format of two prevailing datasets, PROX and GTA-IM, and take them for motion synthesis evaluation in 3D scenes. We also assess the effectiveness of the proposed method in dynamic environments from GTA-IM and Semantic3D to check the responsiveness. The results show our method outperforms previous works significantly and has great performance in handling dynamic environments.
Abstract:Automated machine learning (AutoML) is a collection of techniques designed to automate the machine learning development process. While traditional AutoML approaches have been successfully applied in several critical steps of model development (e.g. hyperparameter optimization), there lacks a AutoML system that automates the entire end-to-end model production workflow. To fill this blank, we present AutoMMLab, a general-purpose LLM-empowered AutoML system that follows user's language instructions to automate the whole model production workflow for computer vision tasks. The proposed AutoMMLab system effectively employs LLMs as the bridge to connect AutoML and OpenMMLab community, empowering non-expert individuals to easily build task-specific models via a user-friendly language interface. Specifically, we propose RU-LLaMA to understand users' request and schedule the whole pipeline, and propose a novel LLM-based hyperparameter optimizer called HPO-LLaMA to effectively search for the optimal hyperparameters. Experiments show that our AutoMMLab system is versatile and covers a wide range of mainstream tasks, including classification, detection, segmentation and keypoint estimation. We further develop a new benchmark, called LAMP, for studying key components in the end-to-end prompt-based model training pipeline. Code, model, and data will be released.