{"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/weakly-supervised-object-discovery-by","title":"Weakly Supervised Object Discovery by Generative Adversarial & Ranking Networks","arxiv_id":"1711.08174","date":"2017-11-22","proceeding":null,"authors":["Ali Diba","Vivek Sharma","Rainer Stiefelhagen","Luc van Gool"],"abstract":"The deep generative adversarial networks (GAN) recently have been shown to be\npromising for different computer vision applications, like image edit- ing,\nsynthesizing high resolution images, generating videos, etc. These networks and\nthe corresponding learning scheme can handle various visual space map- pings.\nWe approach GANs with a novel training method and learning objective, to\ndiscover multiple object instances for three cases: 1) synthesizing a picture\nof a specific object within a cluttered scene; 2) localizing different\ncategories in images for weakly supervised object detection; and 3) improving\nobject discov- ery in object detection pipelines. A crucial advantage of our\nmethod is that it learns a new deep similarity metric, to distinguish multiple\nobjects in one im- age. We demonstrate that the network can act as an\nencoder-decoder generating parts of an image which contain an object, or as a\nmodified deep CNN to rep- resent images for object detection in supervised and\nweakly supervised scheme. Our ranking GAN offers a novel way to search through\nimages for object specific patterns. We have conducted experiments for\ndifferent scenarios and demonstrate the method performance for object\nsynthesizing and weakly supervised object detection and classification using\nthe MS-COCO and PASCAL VOC datasets.","url_abs":"http://arxiv.org/abs/1711.08174v2","url_pdf":"http://arxiv.org/pdf/1711.08174v2.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":"decoder","task_name":"Decoder"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-discovery","task_name":"Object Discovery"},{"task_slug":"weakly-supervised-object-detection","task_name":"Weakly Supervised Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/weakly-supervised-object-detection-on-coco-2","task":"Weakly Supervised Object Detection","dataset":"COCO test-dev","model":"WSGARN+SSD","rank_in_archive_order":2,"of":4,"metrics":{"AP50":"13.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.08174","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}