{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/subcategory-aware-convolutional-neural","title":"Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection","arxiv_id":"1604.04693","date":"2016-04-16","proceeding":null,"authors":["Yu Xiang","Wongun Choi","Yuanqing Lin","Silvio Savarese"],"abstract":"In CNN-based object detection methods, region proposal becomes a bottleneck\nwhen objects exhibit significant scale variation, occlusion or truncation. In\naddition, these methods mainly focus on 2D object detection and cannot estimate\ndetailed properties of objects. In this paper, we propose subcategory-aware\nCNNs for object detection. We introduce a novel region proposal network that\nuses subcategory information to guide the proposal generating process, and a\nnew detection network for joint detection and subcategory classification. By\nusing subcategories related to object pose, we achieve state-of-the-art\nperformance on both detection and pose estimation on commonly used benchmarks.","url_abs":"http://arxiv.org/abs/1604.04693v3","url_pdf":"http://arxiv.org/pdf/1604.04693v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"subcategory-aware-convolutional-neural","repo_url":"https://github.com/xiaohaoChen/rrc_detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"2d-object-detection","task_name":"2D Object Detection"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"region-proposal","task_name":"Region Proposal"},{"task_slug":"vehicle-pose-estimation","task_name":"Vehicle Pose Estimation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-detection-on-pascal-voc-2007","task":"Object Detection","dataset":"PASCAL VOC 2007","model":"subCNN","rank_in_archive_order":23,"of":30,"metrics":{"MAP":"68.5%"},"uses_additional_data":false},{"leaderboard":"/sota/vehicle-pose-estimation-on-kitti-cars-hard","task":"Vehicle Pose Estimation","dataset":"KITTI Cars Hard","model":"SubCNN","rank_in_archive_order":4,"of":19,"metrics":{"Average Orientation Similarity":"78.68"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1604.04693","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}