{"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/relation-preserving-triplet-mining-for","title":"Relation Preserving Triplet Mining for Stabilising the Triplet Loss in Re-identification Systems","arxiv_id":"2110.07933","date":"2021-10-15","proceeding":"Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision 2023 1","authors":["Adhiraj Ghosh","Kuruparan Shanmugalingam","Wen-Yan Lin"],"abstract":"Object appearances change dramatically with pose variations. This creates a challenge for embedding schemes that seek to map instances with the same object ID to locations that are as close as possible. This issue becomes significantly heightened in complex computer vision tasks such as re-identification(reID). In this paper, we suggest that these dramatic appearance changes are indications that an object ID is composed of multiple natural groups, and it is counterproductive to forcefully map instances from different groups to a common location. This leads us to introduce Relation Preserving Triplet Mining (RPTM), a feature-matching guided triplet mining scheme, that ensures that triplets will respect the natural subgroupings within an object ID. We use this triplet mining mechanism to establish a pose-aware, well-conditioned triplet loss by implicitly enforcing view consistency. This allows a single network to be trained with fixed parameters across datasets while providing state-of-the-art results. Code is available at https://github.com/adhirajghosh/RPTM_reid.","url_abs":"https://arxiv.org/abs/2110.07933v2","url_pdf":"https://arxiv.org/pdf/2110.07933v2.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":"relation-preserving-triplet-mining-for","repo_url":"https://github.com/adhirajghosh/rptm_reid","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":null,"task_name":"Relation"},{"task_slug":null,"task_name":"Triplet"},{"task_slug":"vehicle-re-identification","task_name":"Vehicle Re-Identification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/person-re-identification-on-dukemtmc-reid","task":"Person Re-Identification","dataset":"DukeMTMC-reID","model":"RPTM","rank_in_archive_order":12,"of":94,"metrics":{"Rank-1":"93.5","Rank-5":"96.1","mAP":"89.2"},"uses_additional_data":false},{"leaderboard":"/sota/vehicle-re-identification-on-veri-776","task":"Vehicle Re-Identification","dataset":"VeRi-776","model":"RPTM","rank_in_archive_order":2,"of":17,"metrics":{"Rank-1":"97.3","Rank1":"97.3","Rank5":"98.4","mAP":"88.0"},"uses_additional_data":false},{"leaderboard":"/sota/vehicle-re-identification-on-vehicleid-large","task":"Vehicle Re-Identification","dataset":"VehicleID Large","model":"RPTM","rank_in_archive_order":4,"of":10,"metrics":{"Rank-1":"92.9","Rank-5":"96.3","mAP":"80.5"},"uses_additional_data":false},{"leaderboard":"/sota/vehicle-re-identification-on-vehicleid-medium","task":"Vehicle Re-Identification","dataset":"VehicleID Medium","model":"RPTM","rank_in_archive_order":4,"of":9,"metrics":{"Rank-1":"93.3","Rank-5":"96.5","mAP":"81.2"},"uses_additional_data":false},{"leaderboard":"/sota/vehicle-re-identification-on-vehicleid-small","task":"Vehicle Re-Identification","dataset":"VehicleID Small","model":"RPTM","rank_in_archive_order":4,"of":13,"metrics":{"Rank-1":"95.5","Rank-5":"97.4","mAP":"84.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.07933","atlas_url":"https://app.syntology.ai/?focus=2110.07933","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":"2110.07933"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2110.07933\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2110.07933"},"call":"get_concepts_for_paper(arxiv_id=\"2110.07933\")"}],"by_repo":[{"repo":"adhirajghosh/rptm_reid","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1609.01775"],"harvested_for_calls":[{"arxiv_id":"1609.01775","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1609.01775"},"call":"get_harvested_code_for_paper(arxiv_id=\"1609.01775\")"}]}],"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":"b1f9f791b39580aac2fd750c6c28a566d0393b5d5647ad09ed7e2d4574c9b7f4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}