{"id":18076121,"url":"https://github.com/layumi/aicity-reid-2020","last_synced_at":"2025-04-04T22:09:21.095Z","repository":{"id":43904828,"uuid":"257534876","full_name":"layumi/AICIty-reID-2020","owner":"layumi","description":":red_car:  The 1st Place Submission to AICity Challenge 2020 re-id track (Baidu-UTS submission)","archived":false,"fork":false,"pushed_at":"2024-09-01T12:50:07.000Z","size":9151,"stargazers_count":461,"open_issues_count":40,"forks_count":107,"subscribers_count":14,"default_branch":"master","last_synced_at":"2025-03-28T21:08:31.885Z","etag":null,"topics":["aicity","cityflow","cvpr2020","paddlepaddle","pytorch","vehicle","vehicle-reid","veri-776"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/layumi.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2020-04-21T08:47:52.000Z","updated_at":"2025-03-16T10:07:53.000Z","dependencies_parsed_at":"2024-11-14T12:01:29.676Z","dependency_job_id":"57c7199c-7c5c-43c7-bcaf-708c851a2ced","html_url":"https://github.com/layumi/AICIty-reID-2020","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/layumi%2FAICIty-reID-2020","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/layumi%2FAICIty-reID-2020/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/layumi%2FAICIty-reID-2020/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/layumi%2FAICIty-reID-2020/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/layumi","download_url":"https://codeload.github.com/layumi/AICIty-reID-2020/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247256115,"owners_count":20909240,"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","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":["aicity","cityflow","cvpr2020","paddlepaddle","pytorch","vehicle","vehicle-reid","veri-776"],"created_at":"2024-10-31T11:08:54.649Z","updated_at":"2025-04-04T22:09:21.075Z","avatar_url":"https://github.com/layumi.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## AICity-reID 2020 (track2)\n\n![](https://github.com/layumi/AICIty-reID-2020/blob/master/heatmap2020.jpg)\n\nIn this repo, we include the 1st Place submission to [AICity Challenge](https://www.aicitychallenge.org/) 2020 re-id track (Baidu-UTS submission) \n\n[[Paper]](https://github.com/layumi/AICIty-reID-2020/blob/master/paper.pdf) [[Video]](https://www.bilibili.com/video/BV1hK411A78n/)\n\nWe fuse the models trained on Paddlepaddle and Pytorch. To illustrate them, we provide the two training parts seperatively as following. \n\n- We include the [Paddlepaddle](https://github.com/PaddlePaddle/Paddle) training code at [Here](https://github.com/PaddlePaddle/Research/tree/master/CV/PaddleReid).\n- We include the [Pytorch](https://pytorch.org/) training code at [Here](https://github.com/layumi/AICIty-reID-2020/tree/master/pytorch).\n\n### Performance：\n AICITY2020 Challange Track2 Leaderboard\n \n |TeamName|mAP|Link|\n |--------|----|-------|\n |**Baidu-UTS(Ours)**|84.1%|[code](https://github.com/layumi/AICIty-reID-2020)|\n |RuiYanAI|78.1%|[code](https://github.com/Xiangyu-CAS/AICity2020-VOC-ReID)|\n |DMT|73.1%|[code](https://github.com/heshuting555/AICITY2020_DMT_VehicleReID)|\n \n \n### Trained Models \nHow to extract features? Please refer to [[Here]](https://github.com/layumi/AICIty-reID-2020/tree/master/pytorch#extract-feature-for-post-processing) \nand there is one simplified version at [[Here]](https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial#part-21-extracting-feature-python-testpy).\nHere we provide one model of the final models.\n\n- SE_imbalance_s1_384_p0.5_lr2_mt_d0_b24+v+aug (AICity 2020) can be downloaded at [[GoogleDrive]](https://drive.google.com/file/d/1AZ4hHbRbz2T8OHJ6QTG9bR7CP2zUOyQh/view?usp=sharing). \n\nThe state-of-the-art model achieving 83.41% mAP on [VeRi-776](https://github.com/JDAI-CV/VeRidataset), which is based on our TMM paper. \n- Training on VehicelNet only (80.91): Res50_imbalance_s1_256_p0.5_lr2_mt_d0_b48 (TMM) can be downloaded at [[GoogleDrive]](https://drive.google.com/file/d/1wUbYm5-EJs0W-LAGS69yvb33D6NkFWpH/view?usp=sharing).\n- Finetuning on VeRi (83.41): ft_Res50_imbalance_s1_256_p0.5_lr1_mt_d0.2_b48_w5 (TMM) can be downloaded at [[GoogleDrive]](https://drive.google.com/file/d/1Sor7Grh_1Kot6CBLaw2alDT4Nr3JuH3C/view?usp=sharing).\n\n### Extracted Features \u0026 Camera Prediction \u0026 Direction Prediction:\nI have updated the feature. You may download from [GoogleDrive](https://drive.google.com/file/d/1q0ap5smXoRIQ-oEUMbSMMSl_lEOT0Fk6/view?usp=sharing) or [OneDrive](https://studentutsedu-my.sharepoint.com/:u:/g/personal/12639605_student_uts_edu_au/EdxlWLP9bB9Bga0jfDyoIO8Berahz8plAeRY6M4t8g_6iA?e=mSttQx) (expired by July 1 2022)\n```\n├── final_features/\n│   ├── features/                  /* extracted pytorch feature\n│   ├── pkl_feas/                   /* extracted paddle feature (include direction similarity)\n│       ├── real_query_fea_ResNeXt101_32x8d_wsl_416_416_final.pkl \n|           ...\n│       ├── query_fea_Res2Net101_vd_final2.pkl                 \n│   ├── gallery_cam_preds_baidu.txt      /*  gallery camera prediction\n│   ├── query_cam_preds_baidu.txt      /*  query camera prediction\n|   ├── submit_cam.mat             /*  camera feature for camera similarity calculation\n```\n\n### Related Repos：\n\n- :helicopter:  Drone-based building re-id [[code]](https://github.com/layumi/University1652-Baseline)  [[paper]](https://arxiv.org/abs/2002.12186)\n \n- [Vehicle re-ID Paper Collection] https://github.com/layumi/Vehicle_reID-Collection\n\n- [Person re-ID Baseline] https://github.com/layumi/Person_reID_baseline_pytorch\n\n- [Person/Vehicle Generation] https://github.com/NVlabs/DG-Net\n\n### Citation\nPlease cite this paper if it helps your research:\n```bibtex\n@inproceedings{zheng2020going,\n  title={Going beyond real data: A robust visual representation for vehicle re-identification},\n  author={Zheng, Zhedong and Jiang, Minyue and Wang, Zhigang and Wang, Jian and Bai, Zechen and Zhang, Xuanmeng and Yu, Xin and Tan, Xiao and Yang, Yi and Wen, Shilei and others},\n  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},\n  pages={598--599},\n  year={2020}\n}\n\n@article{zheng2020beyond,\n  title={VehicleNet: Learning Robust Visual Representation for Vehicle Re-identification},\n  author={Zheng, Zhedong and Ruan, Tao and Wei, Yunchao and Yang, Yi and Mei, Tao},\n  journal={IEEE Transactions on Multimedia (TMM)},\n  doi={10.1109/TMM.2020.3014488},\n  note={\\mbox{doi}:\\url{10.1109/TMM.2020.3014488}},\n  year={2020}\n}\n```\n\nThe heatmap visualization is based on \n```bibtex\n@article{zheng2017discriminatively,\n  title={A discriminatively learned cnn embedding for person reidentification},\n  author={Zheng, Zhedong and Zheng, Liang and Yang, Yi},\n  journal={ACM transactions on multimedia computing, communications, and applications (TOMM)},\n  volume={14},\n  number={1},\n  pages={1--20},\n  year={2017},\n  publisher={ACM New York, NY, USA}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flayumi%2Faicity-reid-2020","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flayumi%2Faicity-reid-2020","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flayumi%2Faicity-reid-2020/lists"}