{"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/image-image-domain-adaptation-with-preserved","title":"Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification","arxiv_id":"1711.07027","date":"2017-11-19","proceeding":"CVPR 2018 6","authors":["Weijian Deng","Liang Zheng","Qixiang Ye","Guoliang Kang","Yi Yang","Jianbin Jiao"],"abstract":"Person re-identification (re-ID) models trained on one domain often fail to\ngeneralize well to another. In our attempt, we present a \"learning via\ntranslation\" framework. In the baseline, we translate the labeled images from\nsource to target domain in an unsupervised manner. We then train re-ID models\nwith the translated images by supervised methods. Yet, being an essential part\nof this framework, unsupervised image-image translation suffers from the\ninformation loss of source-domain labels during translation.\n  Our motivation is two-fold. First, for each image, the discriminative cues\ncontained in its ID label should be maintained after translation. Second, given\nthe fact that two domains have entirely different persons, a translated image\nshould be dissimilar to any of the target IDs. To this end, we propose to\npreserve two types of unsupervised similarities, 1) self-similarity of an image\nbefore and after translation, and 2) domain-dissimilarity of a translated\nsource image and a target image. Both constraints are implemented in the\nsimilarity preserving generative adversarial network (SPGAN) which consists of\nan Siamese network and a CycleGAN. Through domain adaptation experiment, we\nshow that images generated by SPGAN are more suitable for domain adaptation and\nyield consistent and competitive re-ID accuracy on two large-scale datasets.","url_abs":"http://arxiv.org/abs/1711.07027v3","url_pdf":"http://arxiv.org/pdf/1711.07027v3.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":"image-image-domain-adaptation-with-preserved","repo_url":"https://github.com/Simon4Yan/Learning-via-Translation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"image-image-domain-adaptation-with-preserved","repo_url":"https://github.com/thuml/Transfer-Learning-Library","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"cycle-consistency-loss","method_name":"Cycle Consistency Loss"},{"method_slug":"gan-least-squares-loss","method_name":"GAN Least Squares Loss"},{"method_slug":"instance-normalization","method_name":"Instance Normalization"},{"method_slug":"patchgan","method_name":"PatchGAN"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"siamese-network","method_name":"Siamese Network"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/person-re-identification-on-dukemtmc-reid","task":"Person Re-Identification","dataset":"DukeMTMC-reID","model":"SPGAN+LMP*","rank_in_archive_order":91,"of":94,"metrics":{"Rank-1":"46.4","mAP":"26.2"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-duke-to","task":"Unsupervised Domain Adaptation","dataset":"Duke to Market","model":"SPGAN","rank_in_archive_order":25,"of":26,"metrics":{"mAP":"22.8","rank-1":"51.5","rank-10":"76.8","rank-5":"70.1"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-market-to","task":"Unsupervised Domain Adaptation","dataset":"Market to Duke","model":"SPGAN","rank_in_archive_order":24,"of":25,"metrics":{"mAP":"22.3","rank-1":"41.1","rank-10":"63.0","rank-5":"56.6"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-vehicleid-3","task":"Unsupervised Domain Adaptation","dataset":"VehicleID to VERI-Wild Large","model":"SPGAN","rank_in_archive_order":8,"of":9,"metrics":{"R-1":"47.4","R-10":"-","R-5":"66.1","mAP":"17.5"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-vehicleid-2","task":"Unsupervised Domain Adaptation","dataset":"VehicleID to VERI-Wild Medium","model":"SPGAN","rank_in_archive_order":8,"of":9,"metrics":{"R-1":"55.0","R-10":"-","R-5":"74.5","mAP":"21.6"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-vehicleid","task":"Unsupervised Domain Adaptation","dataset":"VehicleID to VeRi-776","model":"SPGAN","rank_in_archive_order":14,"of":14,"metrics":{"Rank-1":"57.4","Rank-10":"75.6","Rank-5":"70.0","mAP":"16.4"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-person-re-identification-on-5","task":"Unsupervised Person Re-Identification","dataset":"DukeMTMC-reID","model":"SPGAN+LMP","rank_in_archive_order":11,"of":13,"metrics":{"MAP":"26.2","Rank-1":"46.4","Rank-10":"68.0","Rank-5":"62.3"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-person-re-identification-on-6","task":"Unsupervised Person Re-Identification","dataset":"MSMT17->DukeMTMC-reID","model":"SPGAN","rank_in_archive_order":3,"of":4,"metrics":{"Rank-1":"46.4","Rank-10":"68.0","Rank-5":"62.3","mAP":"26.2"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-person-re-identification-on-4","task":"Unsupervised Person Re-Identification","dataset":"Market-1501","model":"SPGAN+LMP","rank_in_archive_order":21,"of":23,"metrics":{"MAP":"26.7","Rank-1":"57.7","Rank-10":"82.4","Rank-5":"75.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1711.07027","atlas_url":"https://app.syntology.ai/?focus=1711.07027","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":"1711.07027"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1711.07027\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1711.07027"},"call":"get_concepts_for_paper(arxiv_id=\"1711.07027\")"}],"by_repo":[{"repo":"Simon4Yan/Learning-via-Translation","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"thuml/Transfer-Learning-Library","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":7,"harvested_for":["1409.7495","1502.02791","1607.01719","1702.05464","1811.12833","1904.05801","2001.01526"],"harvested_for_calls":[{"arxiv_id":"1409.7495","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1409.7495"},"call":"get_harvested_code_for_paper(arxiv_id=\"1409.7495\")"},{"arxiv_id":"1502.02791","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1502.02791"},"call":"get_harvested_code_for_paper(arxiv_id=\"1502.02791\")"},{"arxiv_id":"1607.01719","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1607.01719"},"call":"get_harvested_code_for_paper(arxiv_id=\"1607.01719\")"},{"arxiv_id":"1702.05464","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1702.05464"},"call":"get_harvested_code_for_paper(arxiv_id=\"1702.05464\")"},{"arxiv_id":"1811.12833","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1811.12833"},"call":"get_harvested_code_for_paper(arxiv_id=\"1811.12833\")"},{"arxiv_id":"1904.05801","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1904.05801"},"call":"get_harvested_code_for_paper(arxiv_id=\"1904.05801\")"},{"arxiv_id":"2001.01526","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2001.01526"},"call":"get_harvested_code_for_paper(arxiv_id=\"2001.01526\")"}]}],"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":"087ccef730fc832bcc0864625629ab008053fbe5771100b347b23f480354e8b4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}