{"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/pronet-learning-to-propose-object-specific","title":"ProNet: Learning to Propose Object-specific Boxes for Cascaded Neural Networks","arxiv_id":"1511.03776","date":"2015-11-12","proceeding":"CVPR 2016 6","authors":["Chen Sun","Manohar Paluri","Ronan Collobert","Ram Nevatia","Lubomir Bourdev"],"abstract":"This paper aims to classify and locate objects accurately and efficiently,\nwithout using bounding box annotations. It is challenging as objects in the\nwild could appear at arbitrary locations and in different scales. In this\npaper, we propose a novel classification architecture ProNet based on\nconvolutional neural networks. It uses computationally efficient neural\nnetworks to propose image regions that are likely to contain objects, and\napplies more powerful but slower networks on the proposed regions. The basic\nbuilding block is a multi-scale fully-convolutional network which assigns\nobject confidence scores to boxes at different locations and scales. We show\nthat such networks can be trained effectively using image-level annotations,\nand can be connected into cascades or trees for efficient object\nclassification. ProNet outperforms previous state-of-the-art significantly on\nPASCAL VOC 2012 and MS COCO datasets for object classification and point-based\nlocalization.","url_abs":"http://arxiv.org/abs/1511.03776v3","url_pdf":"http://arxiv.org/pdf/1511.03776v3.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":[],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"object","task_name":"Object"},{"task_slug":"weakly-supervised-object-detection","task_name":"Weakly Supervised Object Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/weakly-supervised-object-detection-on-coco","task":"Weakly Supervised Object Detection","dataset":"COCO (Common Objects in Context)","model":"ProNet","rank_in_archive_order":5,"of":5,"metrics":{"MAP":"43.5"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}