{"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/clip-reid-exploiting-vision-language-model","title":"CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels","arxiv_id":"2211.13977","date":"2022-11-25","proceeding":null,"authors":["Siyuan Li","Li Sun","Qingli Li"],"abstract":"Pre-trained vision-language models like CLIP have recently shown superior performances on various downstream tasks, including image classification and segmentation. However, in fine-grained image re-identification (ReID), the labels are indexes, lacking concrete text descriptions. Therefore, it remains to be determined how such models could be applied to these tasks. This paper first finds out that simply fine-tuning the visual model initialized by the image encoder in CLIP, has already obtained competitive performances in various ReID tasks. Then we propose a two-stage strategy to facilitate a better visual representation. The key idea is to fully exploit the cross-modal description ability in CLIP through a set of learnable text tokens for each ID and give them to the text encoder to form ambiguous descriptions. In the first training stage, image and text encoders from CLIP keep fixed, and only the text tokens are optimized from scratch by the contrastive loss computed within a batch. In the second stage, the ID-specific text tokens and their encoder become static, providing constraints for fine-tuning the image encoder. With the help of the designed loss in the downstream task, the image encoder is able to represent data as vectors in the feature embedding accurately. The effectiveness of the proposed strategy is validated on several datasets for the person or vehicle ReID tasks. Code is available at https://github.com/Syliz517/CLIP-ReID.","url_abs":"https://arxiv.org/abs/2211.13977v4","url_pdf":"https://arxiv.org/pdf/2211.13977v4.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":"clip-reid-exploiting-vision-language-model","repo_url":"https://github.com/syliz517/clip-reid","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"clip-reid-exploiting-vision-language-model","repo_url":"https://github.com/mikel-brostrom/boxmot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"AGPL-3.0"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":"vehicle-re-identification","task_name":"Vehicle Re-Identification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/person-re-identification-on-dukemtmc-reid","task":"Person Re-Identification","dataset":"DukeMTMC-reID","model":"CLIP-ReID (without re-ranking)","rank_in_archive_order":28,"of":94,"metrics":{"Rank-1":"90.8","mAP":"83.1"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-msmt17","task":"Person Re-Identification","dataset":"MSMT17","model":"CLIP-ReID (with re-ranking)","rank_in_archive_order":1,"of":43,"metrics":{"Rank-1":"91.2","mAP":"86.7"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-msmt17","task":"Person Re-Identification","dataset":"MSMT17","model":"CLIP-ReID (without re-ranking)","rank_in_archive_order":9,"of":43,"metrics":{"Rank-1":"89.7","mAP":"75.8"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-market-1501","task":"Person Re-Identification","dataset":"Market-1501","model":"CLIP-ReID (without re-ranking)","rank_in_archive_order":61,"of":135,"metrics":{"Rank-1":" 95.4","mAP":"90.5"},"uses_additional_data":false},{"leaderboard":"/sota/vehicle-re-identification-on-veri-776","task":"Vehicle Re-Identification","dataset":"VeRi-776","model":"CLIP-ReID (without re-ranking)","rank_in_archive_order":6,"of":17,"metrics":{"Rank-1":"97.3","mAP":"84.5"},"uses_additional_data":false},{"leaderboard":"/sota/vehicle-re-identification-on-vehicleid-small","task":"Vehicle Re-Identification","dataset":"VehicleID Small","model":"CLIP-ReID (without re-ranking)","rank_in_archive_order":8,"of":13,"metrics":{"Rank-1":"85.5","Rank-5":"97.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2211.13977","atlas_url":"https://app.syntology.ai/?focus=2211.13977","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":"2211.13977"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2211.13977\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2211.13977"},"call":"get_concepts_for_paper(arxiv_id=\"2211.13977\")"}],"by_repo":[{"repo":"syliz517/clip-reid","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["aaai_25225"],"harvested_for_calls":[]},{"repo":"mikel-brostrom/boxmot","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"bbbca102b8f5fdbabdcb6be39147337074642fd31f2d27ed861d9422d9589432","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}