{"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/progressive-attention-networks-for-visual","title":"Progressive Attention Networks for Visual Attribute Prediction","arxiv_id":"1606.02393","date":"2016-06-08","proceeding":null,"authors":["Paul Hongsuck Seo","Zhe Lin","Scott Cohen","Xiaohui Shen","Bohyung Han"],"abstract":"We propose a novel attention model that can accurately attends to target\nobjects of various scales and shapes in images. The model is trained to\ngradually suppress irrelevant regions in an input image via a progressive\nattentive process over multiple layers of a convolutional neural network. The\nattentive process in each layer determines whether to pass or block features at\ncertain spatial locations for use in the subsequent layers. The proposed\nprogressive attention mechanism works well especially when combined with hard\nattention. We further employ local contexts to incorporate neighborhood\nfeatures of each location and estimate a better attention probability map. The\nexperiments on synthetic and real datasets show that the proposed attention\nnetworks outperform traditional attention methods in visual attribute\nprediction tasks.","url_abs":"http://arxiv.org/abs/1606.02393v5","url_pdf":"http://arxiv.org/pdf/1606.02393v5.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":"progressive-attention-networks-for-visual","repo_url":"https://github.com/hworang77/PAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"hard-attention","task_name":"Hard Attention"},{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}