{"id":20373523,"url":"https://github.com/megengine/icd","last_synced_at":"2025-04-12T06:51:38.113Z","repository":{"id":43490827,"uuid":"426187297","full_name":"MegEngine/ICD","owner":"MegEngine","description":"This is the official implementation of the paper \"Instance-conditional Knowledge Distillation for Object Detection\", based on MegEngine and Pytorch.","archived":false,"fork":false,"pushed_at":"2022-08-07T03:17:12.000Z","size":4485,"stargazers_count":58,"open_issues_count":1,"forks_count":5,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-04-12T06:51:33.765Z","etag":null,"topics":["knowledge-distillation","megengine","object-detection","pytorch"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/MegEngine.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}},"created_at":"2021-11-09T10:36:15.000Z","updated_at":"2025-03-15T15:20:03.000Z","dependencies_parsed_at":"2022-08-30T09:21:07.231Z","dependency_job_id":null,"html_url":"https://github.com/MegEngine/ICD","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/MegEngine%2FICD","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MegEngine%2FICD/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MegEngine%2FICD/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MegEngine%2FICD/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MegEngine","download_url":"https://codeload.github.com/MegEngine/ICD/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248530604,"owners_count":21119595,"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":["knowledge-distillation","megengine","object-detection","pytorch"],"created_at":"2024-11-15T01:18:49.976Z","updated_at":"2025-04-12T06:51:38.093Z","avatar_url":"https://github.com/MegEngine.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Instance-Conditional Knowledge Distillation for Object Detection\nThis is the official implementation of the paper \"Instance-Conditional Knowledge Distillation for Object Detection\", based on [MegEngine](./megengine_release/README.md) and [Pytorch](./pytorch_release/README.md). Go to the desired subfolders for more information and guidance!\n\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"Poster.png\"/\u003e\n\u003c/div\u003e\n\n\u003e [**Instance-Conditional Knowledge Distillation for Object Detection**](https://arxiv.org/abs/2110.12724),            \n\u003e Zijian Kang, Peizhen Zhang, Xiangyu Zhang, Jian Sun, Nanning Zheng         \n\u003e In Proc. of Advances in Neural Information Processing Systems (NeurIPS), 2021            \n\u003e [[arXiv](https://arxiv.org/abs/2110.12724)][[Citation](#citation)][[OpenReview](https://openreview.net/forum?id=k7aeAz4Vbb)]\n\n## Usage \nYou can find two implementations for [MegEngine](./megengine_release/README.md) and [Pytorch](./pytorch_release/README.md) under two sub-folders. We use the latter one to report the performance in the paper. Switch to the subfolder for more information.\n\n### Try it in a few lines :\nTake the detectron2 implementation as an example, you can train your model in a few lines:\n```\ncd pytorch_release\n\n# Install dependancies\npip install pip --upgrade\npip install -r requirements.txt\npip install https://github.com/facebookresearch/detectron2/archive/refs/tags/v0.5.tar.gz\npip install 'git+https://github.com/aim-uofa/AdelaiDet.git@7bf9d87'\n\n# Prepare dataset according to https://github.com/facebookresearch/detectron2/tree/main/datasets\n\n# Train and distill a retinanet detector with ICD\npython3 train_distill.py --num-gpus 8 --resume --config-file configs/Distillation-ICD/retinanet_R_50_R101_icd_FPN_1x.yaml OUTPUT_DIR output/icd_retinanet\n```\n\n## Performance\nFor object detection in MS-COCO:\n| Model         | Baseline (BoxAP)     | + Ours (BoxAP)           | \n| ---           | :---:        | :---:         |\n| Faster R-CNN     | 37.9         | 40.9 (+3.0)        |\n| Retinanet     | 37.4         | 40.7 (+3.3)         |\n| FCOS          | 39.4         | 42.9 (+3.5)         |\n\nFor instance-segmentation in MS-COCO:\n| Model         | Baseline (BoxAP)    | + Ours (BoxAP)          | Baseline (MaskAP)    | + Ours (MaskAP)          | \n| ---           | :---:        | :---:         | :---:        | :---:         |\n| Mask R-CNN     | 38.6        | 41.2 (+2.6)         |  35.2 | 37.4 (+2.2) |\n| SOLOv2     | - | - | 34.6 | 38.5 (+3.9) |\n| CondInst        |39.7 | 43.7 (+4.0) | 35.7 | 39.1 (+3.4) |\n\n## Acknowledgement\n\nSome files are modified from [MegEngine Models](https://github.com/MegEngine/Models) and [Detectron2](https://github.com/facebookresearch/detectron2). We also refer to [Pytorch](https://github.com/pytorch/pytorch), [DETR](https://github.com/facebookresearch/detr) and [AdelaiDet](https://github.com/aim-uofa/AdelaiDet) for some implementations. \n\n\n## License\n\nThis repo is licensed under the Apache License, Version 2.0 (the \"License\").\n\n## Citation\nYou can use the following BibTeX entry for citation in your research.\n```\n@inproceedings{icd_neurips2021,\n author = {Kang, Zijian and Zhang, Peizhen and Zhang, Xiangyu and Sun, Jian and Zheng, Nanning},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {M. Ranzato and A. Beygelzimer and Y. Dauphin and P.S. Liang and J. Wortman Vaughan},\n pages = {16468--16480},\n publisher = {Curran Associates, Inc.},\n title = {Instance-Conditional Knowledge Distillation for Object Detection},\n url = {https://proceedings.neurips.cc/paper/2021/file/892c91e0a653ba19df81a90f89d99bcd-Paper.pdf},\n volume = {34},\n year = {2021}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmegengine%2Ficd","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmegengine%2Ficd","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmegengine%2Ficd/lists"}