{"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/structured-semantic-transfer-for-multi-label","title":"Structured Semantic Transfer for Multi-Label Recognition with Partial Labels","arxiv_id":"2112.10941","date":"2021-12-21","proceeding":null,"authors":["Tianshui Chen","Tao Pu","Hefeng Wu","Yuan Xie","Liang Lin"],"abstract":"Multi-label image recognition is a fundamental yet practical task because real-world images inherently possess multiple semantic labels. However, it is difficult to collect large-scale multi-label annotations due to the complexity of both the input images and output label spaces. To reduce the annotation cost, we propose a structured semantic transfer (SST) framework that enables training multi-label recognition models with partial labels, i.e., merely some labels are known while other labels are missing (also called unknown labels) per image. The framework consists of two complementary transfer modules that explore within-image and cross-image semantic correlations to transfer knowledge of known labels to generate pseudo labels for unknown labels. Specifically, an intra-image semantic transfer module learns image-specific label co-occurrence matrix and maps the known labels to complement unknown labels based on this matrix. Meanwhile, a cross-image transfer module learns category-specific feature similarities and helps complement unknown labels with high similarities. Finally, both known and generated labels are used to train the multi-label recognition models. Extensive experiments on the Microsoft COCO, Visual Genome and Pascal VOC datasets show that the proposed SST framework obtains superior performance over current state-of-the-art algorithms. Codes are available at https://github.com/HCPLab-SYSU/HCP-MLR-PL.","url_abs":"https://arxiv.org/abs/2112.10941v3","url_pdf":"https://arxiv.org/pdf/2112.10941v3.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":"structured-semantic-transfer-for-multi-label","repo_url":"https://github.com/hcplab-sysu/hcp-mlr-pl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"multi-label-image-recognition","task_name":"Multi-Label Image Recognition"},{"task_slug":"multi-label-image-recognition-with-partial","task_name":"Multi-label Image Recognition with Partial Labels"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-label-image-recognition-with-partial","task":"Multi-label Image Recognition with Partial Labels","dataset":"MS-COCO-2014","model":"SST","rank_in_archive_order":6,"of":6,"metrics":{"Average mAP":"76.7"},"uses_additional_data":false},{"leaderboard":"/sota/multi-label-image-recognition-with-partial-1","task":"Multi-label Image Recognition with Partial Labels","dataset":"PASCAL VOC 2007","model":"SST","rank_in_archive_order":6,"of":6,"metrics":{"Average mAP":"90.4"},"uses_additional_data":false},{"leaderboard":"/sota/multi-label-image-recognition-with-partial-2","task":"Multi-label Image Recognition with Partial Labels","dataset":"Visual Genome","model":"SST","rank_in_archive_order":4,"of":4,"metrics":{"Average mAP":"41.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2112.10941","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}