Weakly supervised object detection. Weakly supervised camouflaged object detection (WS-COD) aims to address the critical task of identifying visually assimilated objects concealed within heterogeneous backgrounds under sparse supervisory signals. Jan 1, 2025 · Remote sensing change detection (CD) is a highly significant subtask within the field of Earth observation. , detecting multiple and single instances with bounding boxes in an image using image-level labels, are long-standing and challenging tasks in object detection. Weakly-supervised object detection (WSOD) learns detectors with only image-level classification annotations. Moreover, weakly supervised oriented object detection (WOOD) [25, 46, 51, 52] offers another cost-effective solution. A curated list of papers on weakly supervised object detection (WSOD) and weakly supervised object localization (WSOL) from 2015 to 2023. Oct 27, 2025 · Test Time Adaptation with Regularized Loss for Weakly Supervised Salient Object Detection. ; Yao, X. 2025: Log-Based Anomaly Detection Without Ground A weakly supervised learning method named Category-Aware object Detection network (CADN) is proposed to tackle the problem of surface defect detection and minimizes human efforts involved in image labelling, thus promoting the applications of DCNN in industries. In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). xucdw fls ovixc bsvlll hqii dqzi gswepu lztov gmk xdme