With basic Semi-Supervised Object Detection (SSOD) techniques, one-stage detectors generally obtain limited promotions compared with two-stage clusters. We experimentally find that the root lies in two kinds of ambiguities: (1) Selection ambiguity that selected pseudo labels are less accurate, since classification scores cannot properly represent the localization quality. (2) Assignment ambiguity that samples are matched with improper labels in pseudo-label assignment, as the strategy is misguided by missed objects and inaccurate pseudo boxes. To tackle these problems, we propose a Ambiguity-Resistant Semi-supervised Learning (ARSL) for one-stage detectors. Specifically, to alleviate the selection ambiguity, Joint-Confidence Estimation (JCE) is proposed to jointly quantifies the classification and localization quality of pseudo labels. As for the assignment ambiguity, Task-Separation Assignment (TSA) is introduced to assign labels based on pixel-level predictions rather than unreliable pseudo boxes. It employs a "divide-and-conquer" strategy and separately exploits positives for the classification and localization task, which is more robust to the assignment ambiguity. Comprehensive experiments demonstrate that ARSL effectively mitigates the ambiguities and achieves state-of-the-art SSOD performance on MS COCO and PASCAL VOC. Codes can be found at https://github.com/PaddlePaddle/PaddleDetection.
Tackling Ambiguity from Perspective of Uncertainty Inference and Affinity Diversification for Weakly Supervised Semantic Segmentation
Academy for Engineering & Technology, Fudan University(复旦大学工程与技术学院);Digital Medical Research Center, School of Basic Medical Science, Fudan University(复旦大学基础医学院数字医学研究中心);Shandong Computer Science Center(山东省计算机科学中心)
Don't Guess, Just Ask: Resolving Ambiguity in Referring Segmentation via Multi-turn Clarification
School of Computer Science and Engineering, Sun Yat-sen University(中山大学计算机科学与工程学院);Guangdong Province Key Laboratory of Information Security Technology(广东省信息安全技术重点实验室);Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education(教育部机器智能与先进计算重点实验室)
CRAB: Camera-Radar Fusion for Reducing Depth Ambiguity in Backward Projection based View Transformation
Interdisciplinary Program in Artificial intelligence, Seoul National University(人工智能跨学科项目,首尔国立大学);Cho Chun Shik Graduate School of Mobility, KAIST(移动性研究生院,韩国科学技术院);dot Inc(42dot公司);Electronics and Telecommunications Research Institute (ETRI)(电子电信研究院);Department of Automobile and IT Convergence, Kookmin University(汽车与IT融合系,韩国釜山大学)