{"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/self-paced-deep-learning-for-weakly","title":"Self Paced Deep Learning for Weakly Supervised Object Detection","arxiv_id":"1605.07651","date":"2016-05-24","proceeding":null,"authors":["Enver Sangineto","Moin Nabi","Dubravko Culibrk","Nicu Sebe"],"abstract":"In a weakly-supervised scenario object detectors need to be trained using\nimage-level annotation alone. Since bounding-box-level ground truth is not\navailable, most of the solutions proposed so far are based on an iterative,\nMultiple Instance Learning framework in which the current classifier is used to\nselect the highest-confidence boxes in each image, which are treated as\npseudo-ground truth in the next training iteration. However, the errors of an\nimmature classifier can make the process drift, usually introducing many of\nfalse positives in the training dataset. To alleviate this problem, we propose\nin this paper a training protocol based on the self-paced learning paradigm.\nThe main idea is to iteratively select a subset of images and boxes that are\nthe most reliable, and use them for training. While in the past few years\nsimilar strategies have been adopted for SVMs and other classifiers, we are the\nfirst showing that a self-paced approach can be used with deep-network-based\nclassifiers in an end-to-end training pipeline. The method we propose is built\non the fully-supervised Fast-RCNN architecture and can be applied to similar\narchitectures which represent the input image as a bag of boxes. We show\nstate-of-the-art results on Pascal VOC 2007, Pascal VOC 2010 and ILSVRC 2013.\nOn ILSVRC 2013 our results based on a low-capacity AlexNet network outperform\neven those weakly-supervised approaches which are based on much higher-capacity\nnetworks.","url_abs":"http://arxiv.org/abs/1605.07651v3","url_pdf":"http://arxiv.org/pdf/1605.07651v3.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":"self-paced-deep-learning-for-weakly","repo_url":"https://github.com/moinnabi/SelfPacedDeepLearning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"multiple-instance-learning","task_name":"Multiple Instance Learning"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"weakly-supervised-object-detection","task_name":"Weakly Supervised Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"grouped-convolution","method_name":"Grouped Convolution"},{"method_slug":"local-response-normalization","method_name":"Local Response Normalization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/weakly-supervised-object-detection-on-pascal-1","task":"Weakly Supervised Object Detection","dataset":"PASCAL VOC 2007","model":"Self-Paced Learning","rank_in_archive_order":37,"of":41,"metrics":{"MAP":"38.11"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1605.07651","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}