{"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/learning-super-features-for-image-retrieval-1","title":"Learning Super-Features for Image Retrieval","arxiv_id":"2201.13182","date":"2022-01-31","proceeding":"ICLR 2022 4","authors":["Philippe Weinzaepfel","Thomas Lucas","Diane Larlus","Yannis Kalantidis"],"abstract":"Methods that combine local and global features have recently shown excellent performance on multiple challenging deep image retrieval benchmarks, but their use of local features raises at least two issues. First, these local features simply boil down to the localized map activations of a neural network, and hence can be extremely redundant. Second, they are typically trained with a global loss that only acts on top of an aggregation of local features; by contrast, testing is based on local feature matching, which creates a discrepancy between training and testing. In this paper, we propose a novel architecture for deep image retrieval, based solely on mid-level features that we call Super-features. These Super-features are constructed by an iterative attention module and constitute an ordered set in which each element focuses on a localized and discriminant image pattern. For training, they require only image labels. A contrastive loss operates directly at the level of Super-features and focuses on those that match across images. A second complementary loss encourages diversity. Experiments on common landmark retrieval benchmarks validate that Super-features substantially outperform state-of-the-art methods when using the same number of features, and only require a significantly smaller memory footprint to match their performance. Code and models are available at: https://github.com/naver/FIRe.","url_abs":"https://arxiv.org/abs/2201.13182v1","url_pdf":"https://arxiv.org/pdf/2201.13182v1.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":"learning-super-features-for-image-retrieval-1","repo_url":"https://github.com/naver/fire","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-retrieval-on-roxford-hard","task":"Image Retrieval","dataset":"ROxford (Hard)","model":"FIRe","rank_in_archive_order":6,"of":23,"metrics":{"mAP":"61.2"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-roxford-medium","task":"Image Retrieval","dataset":"ROxford (Medium)","model":"FIRe","rank_in_archive_order":4,"of":23,"metrics":{"mAP":"81.8"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-rparis-hard","task":"Image Retrieval","dataset":"RParis (Hard)","model":"FIRe","rank_in_archive_order":7,"of":23,"metrics":{"mAP":"70.0"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-rparis-medium","task":"Image Retrieval","dataset":"RParis (Medium)","model":"FIRe","rank_in_archive_order":5,"of":23,"metrics":{"mAP":"85.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2201.13182","atlas_url":"https://app.syntology.ai/?focus=2201.13182","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":"2201.13182"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2201.13182\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2201.13182"},"call":"get_concepts_for_paper(arxiv_id=\"2201.13182\")"}],"by_repo":[{"repo":"naver/fire","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":"485b82da4c2f91afc6c95bf812f252b16129f3e1e3c28962f8fe417e2f413595","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}