SGV3D:Towards Scenario Generalization for Vision-based Roadside 3D Object Detection
School of Vehicle and Mobility, Tsinghua University（清华大学车辆与 mobility学院）；Beijing Institute of Technology（北京理工大学）；National University of Singapore（新加坡国立大学）；Beijing University of Chemical Technology（北京化工大学）
Lei Yang, Xinyu Zhang, Jun Li, Li Wang, Chuang Zhang, Li Ju, Zhiwei Li, Yang Shen
Roadside perception can greatly increase the safety of autonomous vehicles by extending their perception ability beyond the visual range and addressing blind spots. However, current state-of-the-art vision-based roadside detection methods possess high accuracy on labeled scenes but have inferior performance on new scenes. This is because roadside cameras remain stationary after installation and can only collect data from a single scene, resulting in the algorithm overfitting these roadside backgrounds and camera poses. To address this issue, in this paper, we propose an innovative Scenario Generalization Framework for Vision-based Roadside 3D Object Detection, dubbed SGV3D. Specifically, we employ a Background-suppressed Module (BSM) to mitigate background overfitting in vision-centric pipelines by attenuating background features during the 2D to bird's-eye-view projection. Furthermore, by introducing the Semi-supervised Data Generation Pipeline (SSDG) using unlabeled images from new scenes, diverse instance foregrounds with varying camera poses are generated, addressing the risk of overfitting specific camera poses. We evaluate our method on two large-scale roadside benchmarks. Our method surpasses all previous methods by a significant margin in new scenes, including +42.57% for vehicle, +5.87% for pedestrian, and +14.89% for cyclist compared to BEVHeight on the DAIR-V2X-I heterologous benchmark. On the larger-scale Rope3D heterologous benchmark, we achieve notable gains of 14.48% for car and 12.41% for large vehicle. We aspire to contribute insights on the exploration of roadside perception techniques, emphasizing their capability for scenario generalization. The code will be available at https://github.com/yanglei18/SGV3D
VanJee Technology（万集科技）；BeiJing Academy of Artificial Intelligence（北京人工智能研究院）
As the roadside perception plays an increasingly significant role in the Connected Automated Vehicle Highway(CAVH) technologies, there are immediate needs of challenging real-world roadside datasets for bench marking and training various computer vision tasks such as 2D/3D object detection and multi-sensor fusion. In this paper, we firstly introduce a challenging BAAI-VANJEE roadside dataset which consist of LiDAR data and RGB images collected by VANJEE smart base station placed on the roadside about 4.5m high. This dataset contains 2500 frames of LiDAR data, 5000 frames of RGB images, includi…
Asymptotic AI；Chalmers University of Technology（查尔姆斯理工大学）；SAFER；Trafikverket（瑞典交通管理局）；Volvo Cars（沃尔沃汽车）
Single-vehicle accidents are the most common type of fatal accidents in Sweden, where a car drives off the road and runs into hazardous roadside objects. Proper installation and maintenance of protective objects, such as crash cushions and guard rails, may reduce the chance and severity of such accidents. Moreover, efficient detection and management of hazardous roadside objects also plays an important role in improving road safety. To better understand the state-of-the-art and system requirements, in this pre-study, we investigate the feasibility, implementation, limitations and scaling up of…
Dynamic V2X Autonomous Perception from Road-to-Vehicle Vision
Suzhou University of Science and Technology（苏州科技大学）；CRIPAC（中国科学院自动化研究所模式识别国家重点实验室）；CASIA（中国科学院自动化研究所）；Suzhou Institute of Trade Commerce（苏州经贸职业技术学院）；Tianjin University（天津大学）
Accurate travel time estimation is paramount for providing transit users with reliable schedules and dependable real-time information. This paper is the first to utilize roadside urban imagery for direct transit travel time prediction. We propose and evaluate an end-to-end framework integrating traditional transit data sources with a roadside camera for automated roadside image data acquisition, labeling, and model training to predict transit travel times across a segment of interest. First, we show how the GTFS real-time data can be utilized as an efficient activation mechanism for a roadside…
BEVHeight: A Robust Framework for Vision-based Roadside 3D Object Detection
State Key Laboratory of Automotive Safety and Energy, Tsinghua University（清华大学汽车安全与节能国家重点实验室）；Autonomous Driving Lab, Alibaba Group（阿里巴巴集团自动驾驶实验室）；Shenzhen Campus, Sun Yat-sen University（中山大学深圳校区）；Center for Machine Learning Research, Peking University（北京大学机器学习研究中心）
University of Galway（戈尔韦大学）；Xperi Corporation（Xperi公司）
Neuromorphic vision or event vision is an advanced vision technology, where in contrast to the visible camera that outputs pixels, the event vision generates neuromorphic events every time there is a brightness change which exceeds a specific threshold in the field of view (FOV). This study focuses on leveraging neuromorphic event data for roadside object detection. This is a proof of concept towards building artificial intelligence (AI) based pipelines which can be used for forward perception systems for advanced vehicular applications. The focus is on building efficient state-of-the-art obje…
Unleashing the Capabilities of Large Vision-Language Models for Intelligent Perception of Roadside Infrastructure
State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (LIESMARS)（信息工程测绘遥感国家重点实验室）；Wuhan University（武汉大学）；Hubei Luojia Laboratory（湖北珞珈实验室）
BEVSpread: Spread Voxel Pooling for Bird's-Eye-View Representation in Vision-based Roadside 3D Object Detection
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Polytechnic Institute, Zhejiang University Baidu（浙江大学百度理工学院）；Zhejiang – Singapore Innovation and AI Joint Research Lab（浙新创新与人工智能联合研究实验室）
CoBEV: Elevating Roadside 3D Object Detection with Depth and Height Complementarity
Zhejiang University（浙江大学）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；University of Oxford（牛津大学）；Hunan University（湖南大学）；Shanghai SUPREMIND Technology Co., Ltd（上海智视科技有限公司）
University of California at Riverside（加州大学河滨分校）；Toyota Motor North America（丰田汽车北美公司）
Object detection plays a fundamental role in enabling Cooperative Driving Automation (CDA), which is regarded as the revolutionary solution to addressing safety, mobility, and sustainability issues of contemporary transportation systems. Although current computer vision technologies could provide satisfactory object detection results in occlusion-free scenarios, the perception performance of onboard sensors could be inevitably limited by the range and occlusion. Owing to flexible position and pose for sensor installation, infrastructure-based detection and tracking systems can enhance the perc…
FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentation
School of Artificial Intelligence, Xidian University（西安电子科技大学人工智能学院）；University of Trento（特伦托大学）；School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机与信息工程学院）
University of Michigan（密歇根大学）；Ford Motor Company（福特汽车公司）
We propose a novel and pragmatic framework for traffic scene perception with roadside cameras. The proposed framework covers a full-stack of roadside perception pipeline for infrastructure-assisted autonomous driving, including object detection, object localization, object tracking, and multi-camera information fusion. Unlike previous vision-based perception frameworks rely upon depth offset or 3D annotation at training, we adopt a modular decoupling design and introduce a landmark-based 3D localization method, where the detection and localization can be well decoupled so that the model can be…
RS2AD: End-to-End Autonomous Driving Data Generation from Roadside Sensor Observations
School of Vehicle and Mobility, Tsinghua University（清华大学车辆与移动系统学院）；State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University（清华大学智能绿色车辆与移动系统国家重点实验室）；School of Instrumentation and Optoelectronic Engineering, BeiHang University（北航仪器与光电工程学院）；Department of Automation, Tsinghua University（清华大学自动化系）
Road maintenance during the Winter season is a safety critical and resource demanding operation. One of its key activities is determining road surface condition (RSC) in order to prioritize roads and allocate cleaning efforts such as plowing or salting. Two conventional approaches for determining RSC are: visual examination of roadside camera images by trained personnel and patrolling the roads to perform on-site inspections. However, with more than 500 cameras collecting images across Ontario, visual examination becomes a resource-intensive activity, difficult to scale especially during perio…
University of Maryland（马里兰大学）；NVIDIA（英伟达）；Caltech（加州理工学院）；Arizona State University（亚利桑那州立大学）
Pre-trained vision-language models (e.g., CLIP) have shown promising zero-shot generalization in many downstream tasks with properly designed text prompts. Instead of relying on hand-engineered prompts, recent works learn prompts using the training data from downstream tasks. While effective, training on domain-specific data reduces a model's generalization capability to unseen new domains. In this work, we propose test-time prompt tuning (TPT), a method that can learn adaptive prompts on the fly with a single test sample. For image classification, TPT optimizes the prompt by minimizing the en…
Bosch Center for AI (BCAI)（博世人工智能中心（BCAI））；Heidelberg University（海德堡大学）；University of Freiburg（弗莱堡大学）
Common deep neural networks (DNNs) for image classification have been shown to rely on shortcut opportunities (SO) in the form of predictive and easy-to-represent visual factors. This is known as shortcut learning and leads to impaired generalization. In this work, we show that common DNNs also suffer from shortcut learning when predicting only basic visual object factors of variation (FoV) such as shape, color, or texture. We argue that besides shortcut opportunities, generalization opportunities (GO) are also an inherent part of real-world vision data and arise from partial independence betw…
Beihang University（北京航空航天大学）；Peking University（北京大学）；Shanghai AI Laboratory（上海人工智能实验室）
Vision Transformers (ViTs) have achieved impressive performance on various vision tasks, yet their generalization under distribution shifts (DS) is rarely understood. In this work, we comprehensively study the out-of-distribution (OOD) generalization of ViTs. For systematic investigation, we first present a taxonomy of DS. We then perform extensive evaluations of ViT variants under different DS and compare their generalization with Convolutional Neural Network (CNN) models. Important observations are obtained: 1) ViTs learn weaker biases on backgrounds and textures, while they are equipped wit…
In the Vision-and-Language Navigation (VLN) task, an agent with egocentric vision navigates to a destination given natural language instructions. The act of manually annotating these instructions is timely and expensive, such that many existing approaches automatically generate additional samples to improve agent performance. However, these approaches still have difficulty generalizing their performance to new environments. In this work, we investigate the popular Room-to-Room (R2R) VLN benchmark and discover that what is important is not only the amount of data you synthesize, but also how yo…
National University of Singapore（新加坡国立大学）；Berkeley（加州大学伯克利分校）
Though vision transformers (ViTs) have exhibited impressive ability for representation learning, we empirically find that they cannot generalize well to unseen domains with previous domain generalization algorithms. In this paper, we propose a novel approach DoPrompt based on prompt learning to embed the knowledge of source domains in domain prompts for target domain prediction. Specifically, domain prompts are prepended before ViT input tokens from the corresponding source domain. Each domain prompt learns domain-specific knowledge efficiently since it is optimized only for one domain. Meanwh…
Revisiting the Generalization Problem of Low-level Vision Models Through the Lens of Image Deraining
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究院，中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）；The Chinese University of Hong Kong（香港中文大学）；Shanghai Jiao Tong University（上海交通大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Shenzhen Key Lab of Computer Vision and Pattern Recognition, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳计算机视觉与模式识别重点实验室，深圳先进技术研究院，中国科学院）；Shenzhen University of Advanced Technology（深圳大学）
Concept-Guided Prompt Learning for Generalization in Vision-Language Models
Harbin Institute of Technology（哈尔滨工业大学）；Southern University of Science and Technology（南方科技大学）；Carnegie Mellon University（卡内基梅隆大学）；Pengcheng Laboratory（鹏城实验室）
Cluster-Aware Neural Collapse Prompt Tuning for Long-Tailed Generalization of Vision-Language Models
Hangzhou Dianzi University（杭州电子科技大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；The Hong Kong Polytechnic University（香港理工大学）；Macao Polytechnic University（澳门理工学院）；Zhejiang Provincial Key Laboratory of Low Altitude Ubiquitous Networking Technology, HDU（浙江省低空 ubiquitous 网络技术重点实验室，HDU）
Nowadays, forgery faces pose pressing security concerns over fake news, fraud, impersonation, etc. Despite the demonstrated success in intra-domain face forgery detection, existing detection methods lack generalization capability and tend to suffer from dramatic performance drops when deployed to unforeseen domains. To mitigate this issue, this paper designs a more general fake face detection model based on the vision transformer(ViT) architecture. In the training phase, the pretrained ViT weights are freezed, and only the Low-Rank Adaptation(LoRA) modules are updated. Additionally, the Single…
