{"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/graph-sampling-based-deep-metric-learning-for","title":"Graph Sampling Based Deep Metric Learning for Generalizable Person Re-Identification","arxiv_id":"2104.01546","date":"2021-04-04","proceeding":"CVPR 2022 1","authors":["Shengcai Liao","Ling Shao"],"abstract":"Recent studies show that, both explicit deep feature matching as well as large-scale and diverse training data can significantly improve the generalization of person re-identification. However, the efficiency of learning deep matchers on large-scale data has not yet been adequately studied. Though learning with classification parameters or class memory is a popular way, it incurs large memory and computational costs. In contrast, pairwise deep metric learning within mini batches would be a better choice. However, the most popular random sampling method, the well-known PK sampler, is not informative and efficient for deep metric learning. Though online hard example mining has improved the learning efficiency to some extent, the mining in mini batches after random sampling is still limited. This inspires us to explore the use of hard example mining earlier, in the data sampling stage. To do so, in this paper, we propose an efficient mini-batch sampling method, called graph sampling (GS), for large-scale deep metric learning. The basic idea is to build a nearest neighbor relationship graph for all classes at the beginning of each epoch. Then, each mini batch is composed of a randomly selected class and its nearest neighboring classes so as to provide informative and challenging examples for learning. Together with an adapted competitive baseline, we improve the state of the art in generalizable person re-identification significantly, by 25.1% in Rank-1 on MSMT17 when trained on RandPerson. Besides, the proposed method also outperforms the competitive baseline, by 6.8% in Rank-1 on CUHK03-NP when trained on MSMT17. Meanwhile, the training time is significantly reduced, from 25.4 hours to 2 hours when trained on RandPerson with 8,000 identities. Code is available at https://github.com/ShengcaiLiao/QAConv.","url_abs":"https://arxiv.org/abs/2104.01546v4","url_pdf":"https://arxiv.org/pdf/2104.01546v4.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":"graph-sampling-based-deep-metric-learning-for","repo_url":"https://github.com/shengcailiao/QAConv","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"generalizable-person-re-identification","task_name":"Generalizable Person Re-identification"},{"task_slug":"graph-sampling","task_name":"Graph Sampling"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/generalizable-person-re-identification-on-22","task":"Generalizable Person Re-identification","dataset":"CUHK03-NP (detected)","model":"QAConv-GS","rank_in_archive_order":2,"of":5,"metrics":{"ClonedPerson->Rank-1":"22.6","ClonedPerson->mAP":"21.8","MSMT17->Rank-1":"20.9","MSMT17->mAP":"20.6","MSMT17-All->Rank-1":"27.6","MSMT17-All->mAP":"28.0","Market-1501->Rank-1":"19.1","Market-1501->mAP":"18.1","RandPerson->Rank-1":"18.4","RandPerson->mAP":"16.1"},"uses_additional_data":true},{"leaderboard":"/sota/generalizable-person-re-identification-on-23","task":"Generalizable Person Re-identification","dataset":"DukeMTMC-reID","model":"QAConv-GS","rank_in_archive_order":4,"of":4,"metrics":{"MSMT17->Rank1":"67.3","MSMT17->mAP":"49.4","MSMT17-All->Rank-1":"71.3","MSMT17-All->mAP":"53.5"},"uses_additional_data":true},{"leaderboard":"/sota/generalizable-person-re-identification-on-20","task":"Generalizable Person Re-identification","dataset":"MSMT17","model":"QAConv-GS","rank_in_archive_order":2,"of":4,"metrics":{"ClonedPerson->Rank-1":"49.1","ClonedPerson->mAP":"18.5","Market-1501->Rank1":"45.9","Market-1501->mAP":"17.2","RandPerson->Rank-1":"45.1","RandPerson->mAP":"15.5"},"uses_additional_data":true},{"leaderboard":"/sota/generalizable-person-re-identification-on-21","task":"Generalizable Person Re-identification","dataset":"Market-1501","model":"QAConv-GS","rank_in_archive_order":2,"of":5,"metrics":{"ClonedPerson->Rank-1":"84.5","ClonedPerson->mAP":"59.9","MSMT17->Rank-1":"79.1","MSMT17->mAP":"49.5","MSMT17-All->Rank-1":"82.4","MSMT17-All->mAP":"56.9","RandPerson->Rank-1":"76.7","RandPerson->mAP":"46.7"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.01546","atlas_url":"https://app.syntology.ai/?focus=2104.01546","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":"2104.01546"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2104.01546\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2104.01546"},"call":"get_concepts_for_paper(arxiv_id=\"2104.01546\")"}],"by_repo":[{"repo":"shengcailiao/QAConv","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2105.14432"],"harvested_for_calls":[{"arxiv_id":"2105.14432","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2105.14432"},"call":"get_harvested_code_for_paper(arxiv_id=\"2105.14432\")"}]}],"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":"73b32d61dcadedb38fdd19c8aec98e2f871dba928a56f09cd7c283414d2c78fd","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}