{"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/end-to-end-learning-of-deep-visual","title":"End-to-end Learning of Deep Visual Representations for Image Retrieval","arxiv_id":"1610.07940","date":"2016-10-25","proceeding":null,"authors":["Albert Gordo","Jon Almazan","Jerome Revaud","Diane Larlus"],"abstract":"While deep learning has become a key ingredient in the top performing methods\nfor many computer vision tasks, it has failed so far to bring similar\nimprovements to instance-level image retrieval. In this article, we argue that\nreasons for the underwhelming results of deep methods on image retrieval are\nthreefold: i) noisy training data, ii) inappropriate deep architecture, and\niii) suboptimal training procedure. We address all three issues.\n  First, we leverage a large-scale but noisy landmark dataset and develop an\nautomatic cleaning method that produces a suitable training set for deep\nretrieval. Second, we build on the recent R-MAC descriptor, show that it can be\ninterpreted as a deep and differentiable architecture, and present improvements\nto enhance it. Last, we train this network with a siamese architecture that\ncombines three streams with a triplet loss. At the end of the training process,\nthe proposed architecture produces a global image representation in a single\nforward pass that is well suited for image retrieval. Extensive experiments\nshow that our approach significantly outperforms previous retrieval approaches,\nincluding state-of-the-art methods based on costly local descriptor indexing\nand spatial verification. On Oxford 5k, Paris 6k and Holidays, we respectively\nreport 94.7, 96.6, and 94.8 mean average precision. Our representations can\nalso be heavily compressed using product quantization with little loss in\naccuracy. For additional material, please see\nwww.xrce.xerox.com/Deep-Image-Retrieval.","url_abs":"http://arxiv.org/abs/1610.07940v2","url_pdf":"http://arxiv.org/pdf/1610.07940v2.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":"end-to-end-learning-of-deep-visual","repo_url":"https://github.com/almazan/deep-image-retrieval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"end-to-end-learning-of-deep-visual","repo_url":"https://github.com/fongyk/graph-attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"end-to-end-learning-of-deep-visual","repo_url":"https://github.com/fongyk/graph-simple","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"end-to-end-learning-of-deep-visual","repo_url":"https://github.com/naver/deep-image-retrieval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":null,"task_name":"Triplet"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-retrieval-on-roxford-medium","task":"Image Retrieval","dataset":"ROxford (Medium)","model":"R–R-MAC","rank_in_archive_order":14,"of":23,"metrics":{"mAP":"60.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1610.07940","atlas_url":"https://app.syntology.ai/?focus=1610.07940","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":"1610.07940"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1610.07940\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1610.07940"},"call":"get_concepts_for_paper(arxiv_id=\"1610.07940\")"}],"by_repo":[{"repo":"almazan/deep-image-retrieval","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1906.07589"],"harvested_for_calls":[{"arxiv_id":"1906.07589","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1906.07589"},"call":"get_harvested_code_for_paper(arxiv_id=\"1906.07589\")"}]},{"repo":"fongyk/graph-attention","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1710.10903"],"harvested_for_calls":[{"arxiv_id":"1710.10903","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1710.10903"},"call":"get_harvested_code_for_paper(arxiv_id=\"1710.10903\")"}]},{"repo":"fongyk/graph-simple","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"naver/deep-image-retrieval","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"a18a6559ddb9094eb0cf5ae7418e18b73b9a885f8c69b875dc26af32b04333e6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}