{"id":23446088,"url":"https://github.com/wangkai930418/dwopp_code","last_synced_at":"2025-08-25T22:10:21.773Z","repository":{"id":167302349,"uuid":"544015034","full_name":"wangkai930418/DwoPP_code","owner":"wangkai930418","description":"code for our BMVC 2022 paper \"Positive Pair Distillation Considered Harmful: Continual Meta Metric Learning for Lifelong Object Re-Identification\"","archived":false,"fork":false,"pushed_at":"2022-10-05T10:15:49.000Z","size":105,"stargazers_count":9,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-13T15:11:50.555Z","etag":null,"topics":["bmvc","continual-learning","incremental-learning","knowledge-distillation","meta-learning","meta-metric-learning","metric-learning","object-reid","person-reid"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/wangkai930418.png","metadata":{"files":{"readme":"readme.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-10-01T12:14:03.000Z","updated_at":"2024-03-04T08:54:24.000Z","dependencies_parsed_at":null,"dependency_job_id":"e1be26db-69d2-4c06-bde2-c87bf479b28c","html_url":"https://github.com/wangkai930418/DwoPP_code","commit_stats":null,"previous_names":["wangkai930418/dwopp_code"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/wangkai930418/DwoPP_code","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wangkai930418%2FDwoPP_code","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wangkai930418%2FDwoPP_code/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wangkai930418%2FDwoPP_code/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wangkai930418%2FDwoPP_code/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wangkai930418","download_url":"https://codeload.github.com/wangkai930418/DwoPP_code/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wangkai930418%2FDwoPP_code/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":272139434,"owners_count":24880307,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-08-25T02:00:12.092Z","response_time":1107,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["bmvc","continual-learning","incremental-learning","knowledge-distillation","meta-learning","meta-metric-learning","metric-learning","object-reid","person-reid"],"created_at":"2024-12-23T20:29:38.598Z","updated_at":"2025-08-25T22:10:21.739Z","avatar_url":"https://github.com/wangkai930418.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# **[Positive Pair Distillation Considered Harmful: Continual Meta Metric Learning for Lifelong Object Re-Identification (BMVC 2022)](https://arxiv.org/abs/2210.01600)**\n\nHere we afford the code to reproduce the experimental results on Market-1501 dataset for our paper *\"Positive Pair Distillation Considered Harmful: Continual Meta Metric Learning for Lifelong Object Re-Identification\".*\n\n[Kai Wang](https://scholar.google.com/citations?user=j14vd0wAAAAJ), [Chenshen Wu](https://scholar.google.com/citations?user=FO7GyVwAAAAJ\u0026hl=en), [Andy Bagdanov](https://scholar.google.com/citations?user=_Fk4YUcAAAAJ\u0026hl=en), [Xialei Liu* (corresponding)](https://mmcheng.net/xliu/), [Shiqi Yang](https://www.shiqiyang.xyz/), Shangling Jui and [Joost van de Weijer](https://scholar.google.com/citations?user=Gsw2iUEAAAAJ\u0026hl=en)\n\n## download dataset\n\nMarket-1501 dataset can be directly downloaded from http://zheng-lab.cecs.anu.edu.au/Project/project_reid.html\n\nAfter extracting the files, you need to have the following files structure:\n```\n|-- market1501  \n        |-- bounding_box_train  \n        |-- bounding_box_test  \n        |-- gt_bbox  \n        |-- gt_query  \n        |-- query  \n        |-- readme.txt\n```\n\nOr if you have already had the dataset locally, you can create a soft link to it by:\n\n```\nln -s /your/path/to/market1501 ./\n```\n## Requirements\n\nAll python packages in my experimental environment is listed in *requirements.txt*\n\n## Reproducing\n\nYou can directly run the bash files as below.\n\n### Market-1501, DwoPP(Our method)\n\n```\nbash CL_DwoPP.sh\n```\n\n### Market-1501, DwPP\n\n```\nbash CL_DwPP.sh\n```\n\n### Market-1501, FT\n\n```\nbash CL_FT.sh\n```\n\n### Market-1501, Joint training\n\n```\nbash joint_train_dmml_market.sh\n```\n\n## Others\nOther datasets cannot be directly downloaded from their websites due to the privacy issue, please contact the datasets authors. If you have any question, do not hesitate to contact me or post an issue.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwangkai930418%2Fdwopp_code","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwangkai930418%2Fdwopp_code","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwangkai930418%2Fdwopp_code/lists"}