{"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/unsupervised-part-based-weighting-aggregation","title":"Unsupervised Part-based Weighting Aggregation of Deep Convolutional Features for Image Retrieval","arxiv_id":"1705.01247","date":"2017-05-03","proceeding":null,"authors":["Jian Xu","Cunzhao Shi","Chengzuo Qi","Chunheng Wang","Baihua Xiao"],"abstract":"In this paper, we propose a simple but effective semantic part-based\nweighting aggregation (PWA) for image retrieval. The proposed PWA utilizes the\ndiscriminative filters of deep convolutional layers as part detectors.\nMoreover, we propose the effective unsupervised strategy to select some part\ndetectors to generate the \"probabilistic proposals\", which highlight certain\ndiscriminative parts of objects and suppress the noise of background. The final\nglobal PWA representation could then be acquired by aggregating the regional\nrepresentations weighted by the selected \"probabilistic proposals\"\ncorresponding to various semantic content. We conduct comprehensive experiments\non four standard datasets and show that our unsupervised PWA outperforms the\nstate-of-the-art unsupervised and supervised aggregation methods. Code is\navailable at https://github.com/XJhaoren/PWA.","url_abs":"http://arxiv.org/abs/1705.01247v3","url_pdf":"http://arxiv.org/pdf/1705.01247v3.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":"unsupervised-part-based-weighting-aggregation","repo_url":"https://github.com/XJhaoren/PWA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}