{"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/deep-imbalanced-attribute-classification","title":"Deep Imbalanced Attribute Classification using Visual Attention Aggregation","arxiv_id":"1807.03903","date":"2018-07-10","proceeding":"ECCV 2018 9","authors":["Nikolaos Sarafianos","Xiang Xu","Ioannis A. Kakadiaris"],"abstract":"For many computer vision applications, such as image description and human\nidentification, recognizing the visual attributes of humans is an essential yet\nchallenging problem. Its challenges originate from its multi-label nature, the\nlarge underlying class imbalance and the lack of spatial annotations. Existing\nmethods follow either a computer vision approach while failing to account for\nclass imbalance, or explore machine learning solutions, which disregard the\nspatial and semantic relations that exist in the images. With that in mind, we\npropose an effective method that extracts and aggregates visual attention masks\nat different scales. We introduce a loss function to handle class imbalance\nboth at class and at an instance level and further demonstrate that penalizing\nattention masks with high prediction variance accounts for the weak supervision\nof the attention mechanism. By identifying and addressing these challenges, we\nachieve state-of-the-art results with a simple attention mechanism in both PETA\nand WIDER-Attribute datasets without additional context or side information.","url_abs":"http://arxiv.org/abs/1807.03903v2","url_pdf":"http://arxiv.org/pdf/1807.03903v2.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":"deep-imbalanced-attribute-classification","repo_url":"https://github.com/cvcode18/imbalanced_learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok"}},{"paper_slug":"deep-imbalanced-attribute-classification","repo_url":"https://github.com/evantkchong/LEPAR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":null,"task_name":"Image Description"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.03903","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}