{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":{"syntology_url":"https://syntology.ai/paper/1805.08587","atlas_url":"https://app.syntology.ai/?focus=1805.08587","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1805.08587"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1805.08587\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1805.08587"},"call":"get_concepts_for_paper(arxiv_id=\"1805.08587\")"}],"by_repo":[{"repo":"MaJinWakeUp/HeWR","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"2f5b9b2a68b2020961ceaf4aab941a21e3e4929bda831afb618c3eaa8623b628","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}