{"id":13737939,"url":"https://github.com/HabibSlim/DKT-for-CIL","last_synced_at":"2025-05-08T15:32:11.927Z","repository":{"id":106054736,"uuid":"406467981","full_name":"HabibSlim/DKT-for-CIL","owner":"HabibSlim","description":"PyTorch implementation of \"Dataset Knowledge Transfer for Class-Incremental Learning Without Memory\" (WACV2022)","archived":false,"fork":false,"pushed_at":"2021-10-21T23:19:54.000Z","size":42523,"stargazers_count":5,"open_issues_count":0,"forks_count":4,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-11T20:08:31.323Z","etag":null,"topics":["computer-vision","continual-learning","deep-learning"],"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/HabibSlim.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}},"created_at":"2021-09-14T17:47:21.000Z","updated_at":"2023-06-05T13:14:03.000Z","dependencies_parsed_at":"2024-01-07T21:14:40.494Z","dependency_job_id":null,"html_url":"https://github.com/HabibSlim/DKT-for-CIL","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/HabibSlim%2FDKT-for-CIL","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HabibSlim%2FDKT-for-CIL/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HabibSlim%2FDKT-for-CIL/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HabibSlim%2FDKT-for-CIL/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/HabibSlim","download_url":"https://codeload.github.com/HabibSlim/DKT-for-CIL/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253096290,"owners_count":21853571,"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","continual-learning","deep-learning"],"created_at":"2024-08-03T03:02:06.514Z","updated_at":"2025-05-08T15:32:06.917Z","avatar_url":"https://github.com/HabibSlim.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\u003ch1 align=\"center\"\u003e\n    Dataset Knowledge Transfer for Class-Incremental Learning Without Memory\n\u003c/h1\u003e\n\n[![Python](https://img.shields.io/badge/Python-3.8.5-blue?logo=python\u0026logoColor=white)](https://www.python.org/)\n[![PyTorch](https://img.shields.io/badge/Pytorch-1.7.1-red?logo=pytorch\u0026logoColor=white)](https://pytorch.org/)\n\n\\[[Paper](https://arxiv.org/abs/2110.08421)\\] \\[[Slides](http://todo.todo)\\]\n\n\u003cp align=\"center\"\u003e\n    \u003cimg src=\"./img/main_fig.svg\" width=600px/\u003e\n\u003c/p\u003e\n\u003c/div\u003e\n\n\n## Summary\n\n* [Introduction](#introduction)\n* [Installation](#installation)\n* [Reproducing results](#reproducing-results)\n* [Citation](#citation)\n* [Acknowledgments](#acknowledgments)\n\n## Introduction\n\nThis repository contains the PyTorch implementation for the [WACV 2022](https://wacv2022.thecvf.com/) Paper [\"Dataset Knowledge Transfer for Class-Incremental Learning Without Memory\"](https://arxiv.org/abs/2110.08421).\nThis paper is the result of an internship research project conducted at [CEA-LIST](http://www-list.cea.fr/en/). Our work tackles bias-correction in incrementally learned models when no rehearsal memory is available (check out the [paper](https://arxiv.org/abs/2110.08421) for more info!).\n\nFeel free to open a GitHub issue if you encounter any problem with the code, or if you have any question about the paper.\n\n\n## Installation\n\nInstall the environments required to run the project with the following commands:\n\n```bash\nconda env create -f ./envs/FACIL.yml\nconda env create -f ./envs/iCaRL.yml\n```\n\nFor more details, read the \u003ccode\u003e./envs/README.md\u003c/code\u003e file.\nYou will also need to extract image lists if you want to reuse the datasets presented in our paper. In order to do that, you can check the \u003ccode\u003e./datasets/README.md\u003c/code\u003e file.\n\n## Reproducing results\n\nTo reproduce results reported in our paper, we pre-extracted output scores on top of __LUCIR__ and __LwF__ and provide them in this repository for __CIFAR-100__ and __S=10__. Run the following command:\n\n```bash\nsource ./scripts/run_eval.sh {lucir or lwf}\n```\n\nFor instructions on how to train and run on top of all other methods/datasets, please read the \u003ccode\u003e./scripts/README.md\u003c/code\u003e file.\n\n\n## Citation\n\nIf our paper is helpful for your work, please consider citing it!\n\n```bibtex\n@inproceedings{slim2022_transil,\n    author    = {Slim, Habib and Belouadah, Eden and Popescu, Adrian and Onchis, Darian},\n    title     = {Dataset Knowledge Transfer for Class-Incremental Learning Without Memory},\n    booktitle = {The IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},\n    year      = {2022}\n}\n```\n\n## Acknowledgments\n\nThis repository uses source code from repositories listed below:\n\n* [FACIL Framework](https://github.com/mmasana/FACIL)\n\n* [LUCIR](https://github.com/hshustc/CVPR19_Incremental_Learning)\n\n* [iCaRL (LwF)](https://github.com/srebuffi/iCaRL)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FHabibSlim%2FDKT-for-CIL","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FHabibSlim%2FDKT-for-CIL","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FHabibSlim%2FDKT-for-CIL/lists"}