{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/learning-spatial-regularization-with-image","title":"Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification","arxiv_id":"1702.05891","date":"2017-02-20","proceeding":"CVPR 2017 7","authors":["Feng Zhu","Hongsheng Li","Wanli Ouyang","Nenghai Yu","Xiaogang Wang"],"abstract":"Multi-label image classification is a fundamental but challenging task in\ncomputer vision. Great progress has been achieved by exploiting semantic\nrelations between labels in recent years. However, conventional approaches are\nunable to model the underlying spatial relations between labels in multi-label\nimages, because spatial annotations of the labels are generally not provided.\nIn this paper, we propose a unified deep neural network that exploits both\nsemantic and spatial relations between labels with only image-level\nsupervisions. Given a multi-label image, our proposed Spatial Regularization\nNetwork (SRN) generates attention maps for all labels and captures the\nunderlying relations between them via learnable convolutions. By aggregating\nthe regularized classification results with original results by a ResNet-101\nnetwork, the classification performance can be consistently improved. The whole\ndeep neural network is trained end-to-end with only image-level annotations,\nthus requires no additional efforts on image annotations. Extensive evaluations\non 3 public datasets with different types of labels show that our approach\nsignificantly outperforms state-of-the-arts and has strong generalization\ncapability. Analysis of the learned SRN model demonstrates that it can\neffectively capture both semantic and spatial relations of labels for improving\nclassification performance.","url_abs":"http://arxiv.org/abs/1702.05891v2","url_pdf":"http://arxiv.org/pdf/1702.05891v2.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":"learning-spatial-regularization-with-image","repo_url":"https://github.com/zhufengx/SRN_multilabel","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"learning-spatial-regularization-with-image","repo_url":"https://github.com/Enjia/Spatial-Regularization-Network-in-Tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"multi-label-classification","task_name":"Multi-Label Classification"},{"task_slug":"multi-label-image-classification","task_name":"Multi-Label Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-label-classification-on-ms-coco","task":"Multi-Label Classification","dataset":"MS-COCO","model":"ResNet-SRN","rank_in_archive_order":34,"of":34,"metrics":{"mAP":"77.1"},"uses_additional_data":false},{"leaderboard":"/sota/multi-label-classification-on-nus-wide","task":"Multi-Label Classification","dataset":"NUS-WIDE","model":"SRN","rank_in_archive_order":6,"of":9,"metrics":{"MAP":"62.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1702.05891","atlas_url":"https://app.syntology.ai/?focus=1702.05891","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1702.05891"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1702.05891\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1702.05891"},"call":"get_concepts_for_paper(arxiv_id=\"1702.05891\")"}],"by_repo":[{"repo":"zhufengx/SRN_multilabel","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Enjia/Spatial-Regularization-Network-in-Tensorflow","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"298d5a287d33debdcf83a4f252d08a490545d8d72800c262a511c15b1cd8bf1c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}