{"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/particular-object-retrieval-with-integral-max","title":"Particular object retrieval with integral max-pooling of CNN activations","arxiv_id":"1511.05879","date":"2015-11-18","proceeding":null,"authors":["Giorgos Tolias","Ronan Sicre","Hervé Jégou"],"abstract":"Recently, image representation built upon Convolutional Neural Network (CNN)\nhas been shown to provide effective descriptors for image search, outperforming\npre-CNN features as short-vector representations. Yet such models are not\ncompatible with geometry-aware re-ranking methods and still outperformed, on\nsome particular object retrieval benchmarks, by traditional image search\nsystems relying on precise descriptor matching, geometric re-ranking, or query\nexpansion. This work revisits both retrieval stages, namely initial search and\nre-ranking, by employing the same primitive information derived from the CNN.\nWe build compact feature vectors that encode several image regions without the\nneed to feed multiple inputs to the network. Furthermore, we extend integral\nimages to handle max-pooling on convolutional layer activations, allowing us to\nefficiently localize matching objects. The resulting bounding box is finally\nused for image re-ranking. As a result, this paper significantly improves\nexisting CNN-based recognition pipeline: We report for the first time results\ncompeting with traditional methods on the challenging Oxford5k and Paris6k\ndatasets.","url_abs":"http://arxiv.org/abs/1511.05879v2","url_pdf":"http://arxiv.org/pdf/1511.05879v2.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":"particular-object-retrieval-with-integral-max","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":"particular-object-retrieval-with-integral-max","repo_url":"https://github.com/facebookresearch/videoalignment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"particular-object-retrieval-with-integral-max","repo_url":"https://github.com/gtolias/rmac","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"particular-object-retrieval-with-integral-max","repo_url":"https://github.com/moabitcoin/sisyphus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"particular-object-retrieval-with-integral-max","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"}},{"paper_slug":"particular-object-retrieval-with-integral-max","repo_url":"https://github.com/talal579/Deep-image-matching","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"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":[{"leaderboard":"/sota/image-retrieval-on-oxf105k","task":"Image Retrieval","dataset":"Oxf105k","model":"R-MAC+R+QE","rank_in_archive_order":7,"of":9,"metrics":{"MAP":"73.2%"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-oxf105k","task":"Image Retrieval","dataset":"Oxf105k","model":"R-MAC","rank_in_archive_order":8,"of":9,"metrics":{"MAP":"61.6%"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-par106k","task":"Image Retrieval","dataset":"Par106k","model":"R-MAC+R+QE","rank_in_archive_order":5,"of":7,"metrics":{"mAP":"79.8%"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-par106k","task":"Image Retrieval","dataset":"Par106k","model":"R-MAC","rank_in_archive_order":7,"of":7,"metrics":{"mAP":"75.7%"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-par6k","task":"Image Retrieval","dataset":"Par6k","model":"R-MAC+R+QE","rank_in_archive_order":4,"of":7,"metrics":{"mAP":"86.5%"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-par6k","task":"Image Retrieval","dataset":"Par6k","model":"R-MAC","rank_in_archive_order":7,"of":7,"metrics":{"mAP":"83.0%"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-roxford-hard","task":"Image Retrieval","dataset":"ROxford (Hard)","model":"R–R-MAC","rank_in_archive_order":18,"of":23,"metrics":{"mAP":"32.4 "},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-roxford-hard","task":"Image Retrieval","dataset":"ROxford (Hard)","model":"R – [O] –MAC","rank_in_archive_order":20,"of":23,"metrics":{"mAP":"18.0 "},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-roxford-medium","task":"Image Retrieval","dataset":"ROxford (Medium)","model":"R – [O] –MAC","rank_in_archive_order":21,"of":23,"metrics":{"mAP":"41.7"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-rparis-hard","task":"Image Retrieval","dataset":"RParis (Hard)","model":"R–R-MAC","rank_in_archive_order":10,"of":23,"metrics":{"mAP":"59.4 "},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-rparis-hard","task":"Image Retrieval","dataset":"RParis (Hard)","model":"R – [O] –MAC","rank_in_archive_order":18,"of":23,"metrics":{"mAP":"44.1"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-rparis-medium","task":"Image Retrieval","dataset":"RParis (Medium)","model":"R–R-MAC","rank_in_archive_order":9,"of":23,"metrics":{"mAP":"78.9 "},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-rparis-medium","task":"Image Retrieval","dataset":"RParis (Medium)","model":"R – [O] –MAC","rank_in_archive_order":18,"of":23,"metrics":{"mAP":"66.2 "},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1511.05879","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.05879"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/videoalignment","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gtolias/rmac","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/talal579/Deep-image-matching","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/moabitcoin/sisyphus","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/naver/deep-image-retrieval","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/almazan/deep-image-retrieval","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"unverified":4},"by_repo_kind":{"listed":{"samples":4,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"4283d78cc976f626","entry":"files","repo":"moabitcoin/sisyphus","repo_kind":"listed","path":"sfi/utils.py","file_url":"https://github.com/moabitcoin/sisyphus/blob/HEAD/sfi/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4283d78cc976f626"}},{"code_sha256_prefix":"43635e94cbab381a","entry":"fileslist","repo":"moabitcoin/sisyphus","repo_kind":"listed","path":"sfi/utils.py","file_url":"https://github.com/moabitcoin/sisyphus/blob/HEAD/sfi/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"43635e94cbab381a"}},{"code_sha256_prefix":"13336f591d395532","entry":"pad_to_multiple","repo":"moabitcoin/sisyphus","repo_kind":"listed","path":"sfi/transforms.py","file_url":"https://github.com/moabitcoin/sisyphus/blob/HEAD/sfi/transforms.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"13336f591d395532"}},{"code_sha256_prefix":"876c7e2b4b89a923","entry":"to_image_mode","repo":"moabitcoin/sisyphus","repo_kind":"listed","path":"sfi/transforms.py","file_url":"https://github.com/moabitcoin/sisyphus/blob/HEAD/sfi/transforms.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"876c7e2b4b89a923"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}