{"id":13737997,"url":"https://github.com/dahyun-kang/ifsl","last_synced_at":"2025-04-12T23:26:43.215Z","repository":{"id":40508974,"uuid":"465765341","full_name":"dahyun-kang/ifsl","owner":"dahyun-kang","description":"[CVPR'22] Official PyTorch implementation of Integrative Few-Shot Learning for Classification and Segmentation","archived":false,"fork":false,"pushed_at":"2024-01-02T02:30:12.000Z","size":8951,"stargazers_count":126,"open_issues_count":0,"forks_count":16,"subscribers_count":5,"default_branch":"main","last_synced_at":"2024-11-15T06:33:04.042Z","etag":null,"topics":["computer-vision","cvpr2022","deep-learning","few-shot-classification","few-shot-learning","few-shot-segmentation","pytorch","pytorch-lightning"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/2203.15712","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/dahyun-kang.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}},"created_at":"2022-03-03T15:00:04.000Z","updated_at":"2024-11-13T10:17:34.000Z","dependencies_parsed_at":"2024-01-02T03:40:53.265Z","dependency_job_id":null,"html_url":"https://github.com/dahyun-kang/ifsl","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/dahyun-kang%2Fifsl","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dahyun-kang%2Fifsl/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dahyun-kang%2Fifsl/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dahyun-kang%2Fifsl/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dahyun-kang","download_url":"https://codeload.github.com/dahyun-kang/ifsl/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248645614,"owners_count":21138840,"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":["computer-vision","cvpr2022","deep-learning","few-shot-classification","few-shot-learning","few-shot-segmentation","pytorch","pytorch-lightning"],"created_at":"2024-08-03T03:02:08.522Z","updated_at":"2025-04-12T23:26:43.189Z","avatar_url":"https://github.com/dahyun-kang.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n  \u003ch1\u003e Integrative Few-Shot Learning \u003cbr\u003e for Classification and Segmentation\u003c/h1\u003e\n\u003c/div\u003e\n\n\u003cdiv align=\"center\"\u003e\n  \u003ch3\u003e\u003ca href=http://dahyun-kang.github.io\u003eDahyun Kang\u003c/a\u003e \u0026nbsp;\u0026nbsp;\u0026nbsp;\u0026nbsp; \u003ca href=http://cvlab.postech.ac.kr/~mcho/\u003eMinsu Cho\u003c/a\u003e\u003c/h3\u003e\n\u003c/div\u003e\n\u003cbr /\u003e\n\n\n\u003cdiv align=\"center\"\u003e\n  \u003ca href=\"https://arxiv.org/abs/2203.15712\"\u003e\u003cimg src=\"https://img.shields.io/badge/arXiv-2203.15712-b31b1b.svg\"/\u003e\u003c/a\u003e\n  \u003ca href=\"http://cvlab.postech.ac.kr/research/iFSL\"\u003e\u003cimg src=\"https://img.shields.io/static/v1?label=project homepage\u0026message=iFSL\u0026color=9cf\"/\u003e\u003c/a\u003e\n\u003c/div\u003e\n\u003cbr /\u003e\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"fs-cs/data/assets/teaser.png\" alt=\"result\" width=\"600\"/\u003e\n\u003c/div\u003e\n\nThis repo is the official implementation of the CVPR 2022 paper: [Integrative Few-Shot Learning for Classification and Segmentation](https://arxiv.org/abs/2203.15712).\n\n\n## :scroll: BibTex source\nIf you find our code or paper useful, please consider citing our paper:\n\n```BibTeX\n@inproceedings{kang2022ifsl,\n  author   = {Kang, Dahyun and Cho, Minsu},\n  title    = {Integrative Few-Shot Learning for Classification and Segmentation},\n  booktitle= {Proceedings of the {IEEE/CVF} Conference on Computer Vision and Pattern Recognition (CVPR)},\n  year     = {2022}\n}\n```\n\n\n## :gear: Conda environmnet installation\nThis project is built upon the following environment:\n* [Ubuntu 16.04](https://ubuntu.com/download)\n* [Python 3.7](https://pytorch.org)\n* [CUDA 11.0](https://developer.nvidia.com/cuda-toolkit)\n* [PyTorch 1.7.0](https://pytorch.org)\n\nThe package requirements can be installed via `environment.yml`, which includes\n* [`pytorch`](https://pytorch.org)==1.7.0\n* [`torchvision`](https://pytorch.org/vision/stable/index.html)==0.8.1\n* [`cudatoolkit`](https://developer.nvidia.com/cuda-toolkit)==11.0.3\n* [`pytorch-lightning`](https://www.pytorchlightning.ai/)==1.3.8\n* [`einops`](https://einops.rocks/pytorch-examples.html)==0.3.0\n```bash\nconda env create --name ifsl_pytorch1.7.0 --file environment.yml -p YOURCONDADIR/envs/ifsl_pytorch1.7.0\nconda activate ifsl_pytorch1.7.0\n```\nMake sure to replace `YOURCONDADIR` in the installation path with your conda dir, e.g., `~/anaconda3`\n\n## :books: Datasets\n* [PASCAL VOC 2012](http://host.robots.ox.ac.uk/pascal/VOC/voc2012/) and [SBD](http://home.bharathh.info/pubs/codes/SBD/download.html)\n* [Microsoft COCO 2014](https://cocodataset.org/#download)\n\nDownload the datasets by following the file structure below and set `args.datapath=YOUR_DATASET_DIR`:\n\n```\n    YOUR_DATASET_DIR/\n    ├── VOC2012/\n    │   ├── Annotations/\n    │   ├── JPEGImages/\n    │   ├── ...\n    ├── COCO2014/\n    │   ├── annotations/\n    │   ├── train2014/\n    │   ├── val2014/\n    │   ├── ...\n    ├── ...\n```\n\nWe follow the dataset protocol of [HSNet](https://github.com/juhongm999/hsnet) and [PFENet](https://github.com/dvlab-research/PFENet).\n\n\n## :mag: Related repos\nOur project refers to and heavily borrows some the codes from the following repos:\n\n* [[PANet]](https://github.com/kaixin96/PANet): Wang _et al_.,  Few-shot image semantic segmentation with prototype alignment, ICCV'19.\n* [[PFENet]](https://github.com/dvlab-research/PFENet): Tian _et al_., Prior guided feature enrichment network for few-shot segmentation, TPAMI'20.\n* [[HSNet]](https://github.com/juhongm999/hsnet):  Min _et al_., Hypercorrelation squeeze for few-shot segmentation, ICCV'21.\n\n\n## :bow: Acknowledgements\nThis work was supported by Samsung Advanced Institute of Technology (SAIT) and also by Center for Applied Research in Artificial Intelligence (CARAI) grant funded by DAPA and ADD (UD190031RD).\nWe also thank [Ahyun Seo](https://github.com/ahyunSeo) and [Deunsol Jung](https://github.com/hesedjds) for their helpful discussion.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdahyun-kang%2Fifsl","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdahyun-kang%2Fifsl","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdahyun-kang%2Fifsl/lists"}