{"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-feature-aggregation-and-image-re-ranking","title":"Deep Feature Aggregation and Image Re-ranking with Heat Diffusion for Image Retrieval","arxiv_id":"1805.08587","date":"2018-05-22","proceeding":null,"authors":["Shanmin Pang","Jin Ma","Jianru Xue","Jihua Zhu","Vicente Ordonez"],"abstract":"Image retrieval based on deep convolutional features has demonstrated\nstate-of-the-art performance in popular benchmarks. In this paper, we present a\nunified solution to address deep convolutional feature aggregation and image\nre-ranking by simulating the dynamics of heat diffusion. A distinctive problem\nin image retrieval is that repetitive or \\emph{bursty} features tend to\ndominate final image representations, resulting in representations less\ndistinguishable. We show that by considering each deep feature as a heat\nsource, our unsupervised aggregation method is able to avoid\nover-representation of \\emph{bursty} features. We additionally provide a\npractical solution for the proposed aggregation method and further show the\nefficiency of our method in experimental evaluation. Inspired by the\naforementioned deep feature aggregation method, we also propose a method to\nre-rank a number of top ranked images for a given query image by considering\nthe query as the heat source. Finally, we extensively evaluate the proposed\napproach with pre-trained and fine-tuned deep networks on common public\nbenchmarks and show superior performance compared to previous work.","url_abs":"http://arxiv.org/abs/1805.08587v5","url_pdf":"http://arxiv.org/pdf/1805.08587v5.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-feature-aggregation-and-image-re-ranking","repo_url":"https://github.com/MaJinWakeUp/HeWR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"re-ranking","task_name":"Re-Ranking"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.08587","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}