This paper presents the Rail-5k dataset for benchmarking the performance of visual algorithms in a real-world application scenario, namely the rail surface defects detection task. We collected over 5k high-quality images from railways across China, and annotated 1100 images with the help from railway experts to identify the most common 13 types of rail defects. The dataset can be used for two settings both with unique challenges, the first is the fully-supervised setting using the 1k+ labeled images for training, fine-grained nature and long-tailed distribution of defect classes makes it hard for visual algorithms to tackle. The second is the semi-supervised learning setting facilitated by the 4k unlabeled images, these 4k images are uncurated containing possible image corruptions and domain shift with the labeled images, which can not be easily tackle by previous semi-supervised learning methods. We believe our dataset could be a valuable benchmark for evaluating robustness and reliability of visual algorithms.
Towards Railway Domain Adaptation for LiDAR-based 3D Detection: Road-to-Rail and Sim-to-Real via SynDRA-BBox
Mobility Technologies（移动技术）；Department of Excellence in Robotics & AI, SETLabs Research GmbH（机器人与人工智能卓越部门，SETLabs Research GmbH）；Scuola Superiore Sant’Anna（圣安娜高等学院）
No-Service Rail Surface Defect Segmentation via Normalized Attention and Dual-scale Interaction
Shanghai University（上海大学）；Shanghai Institute for Advanced Communication and Data Science（上海先进通信与数据科学研究院）；School of Communication and Information Engineering, Shanghai University（上海大学通信与信息工程学院）；Wenzhou Institute of Shanghai University（上海大学温州研究院）
Self-Supervised Topologically Invariant Manifold Learning for Railway Image Quality Assessment
CRRC Chongqing Co., Ltd.（中车重庆有限公司）；College of Computer Science, Sichuan University（四川大学计算机学院）；School of Artificial Intelligence, Hebei University of Technology（河北工业大学人工智能学院）；State Key Laboratory of Mechanical Transmission for Advanced Equipment, Chongqing University（重庆大学先进装备机械传动国家重点实验室）；College of Mathematics and Statistics, Chongqing University（重庆大学数学与统计学院）
A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospects
State Key Laboratory of Intelligent Manufacturing Equipment and Technology, Huazhong University of Science and Technology（智能制造装备与技术国家重点实验室，华中科技大学）；School of Artificial Intelligence and Robotics, Hunan University（人工智能与机器人学院，湖南大学）；Department of Precision Instrument, Tsinghua University（精密仪器系，清华大学）；Geely Automobile Research Institute (Ningbo) Co., Ltd.（吉利汽车研究院（宁波）有限公司）
GDDS: A Single Domain Generalized Defect Detection Frame of Open World Scenario using Gather and Distribute Domain-shift Suppression Network
College of Artificial Intelligence and Data Science（人工智能与数据科学学院）；College of Electronic Science（电子科学学院）；Tianjin Advanced Technology Research Institute（天津先进技术研究院）
