{"id":17897967,"url":"https://github.com/grypesc/seed","last_synced_at":"2025-07-09T06:07:12.648Z","repository":{"id":217856786,"uuid":"733020642","full_name":"grypesc/SEED","owner":"grypesc","description":"ICLR2024 paper on Continual Learning","archived":false,"fork":false,"pushed_at":"2024-04-21T19:44:38.000Z","size":437,"stargazers_count":33,"open_issues_count":0,"forks_count":7,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-18T19:30:03.295Z","etag":null,"topics":["class-incremental","class-incremental-learning","computer-vision","continual-learning","facil","machine-learning"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/2401.10191","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/grypesc.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":"2023-12-18T11:37:48.000Z","updated_at":"2025-02-27T07:55:40.000Z","dependencies_parsed_at":"2024-02-21T11:24:47.882Z","dependency_job_id":"91f1cada-06c0-4879-bc5e-365a29b3a1ae","html_url":"https://github.com/grypesc/SEED","commit_stats":null,"previous_names":["grypesc/seed"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/grypesc%2FSEED","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/grypesc%2FSEED/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/grypesc%2FSEED/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/grypesc%2FSEED/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/grypesc","download_url":"https://codeload.github.com/grypesc/SEED/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245078067,"owners_count":20557274,"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":["class-incremental","class-incremental-learning","computer-vision","continual-learning","facil","machine-learning"],"created_at":"2024-10-28T15:22:06.460Z","updated_at":"2025-03-23T08:32:20.174Z","avatar_url":"https://github.com/grypesc.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Divide and not forget: Ensemble of selectively trained experts in Continual Learning: ICLR2024 (Main track)\n\nhttps://arxiv.org/abs/2401.10191  \nhttps://openreview.net/forum?id=sSyytcewxe  \n\n![image](inference.jpg?raw=true \"inference\")\n\nThis repository contains code for the SEED paper published at the main track of ICLR2024. It is based on FACIL (https://github.com/mmasana/FACIL) benchmark.\nTo reproduce results run one of provided scripts. \n\nSetup environment according to readme of FACIL.\n\nRun SEED on CIFAR100 10 tasks, 10 classes each:\n```bash\nbash cifar10x10.sh\n```\n\nRun SEED on CIFAR100 20 tasks, 5 classes each:\n```bash\nbash cifar20x5.sh\n```\n\nRun SEED on CIFAR100 50 tasks, 2 classes each:\n```bash\nbash cifar50x2.sh\n```\nTo lower the number of parameters as in Tab.5 use ```--network resnet 20 --shared 2```. You can also add parameter pruning as in DER.\n\nTo reproduce results for ImageNet Subset download ImageNet subset from https://www.kaggle.com/datasets/arjunashok33/imagenet-subset-for-inc-learn and unzip it in ```../data``` directory.\n```bash\nbash imagenet10x10.sh\n```\n\nTo reproduce results for DomainNet download it from http://ai.bu.edu/M3SDA/ and put it in ```../data/domainnet``` directory (unzip it).\nRun SEED on DomainNet 36 tasks of different domains, 5 classes each:\n```bash\nbash domainnet36x5.sh\n```\nYou can add ```--extra-aug fetril``` flag to enable better augmentations.\n\nIf you would like to cooperate on improving the method, please contact me via LinkedIn or Facebook, I have several ideas.\n\nIf you find this work useful, please consider citing it:\n\n```\n@inproceedings{rypesc2023divide,\n  title={Divide and not forget: Ensemble of selectively trained experts in Continual Learning},\n  author={Rype{\\'s}{\\'c}, Grzegorz and Cygert, Sebastian and Khan, Valeriya and Trzcinski, Tomasz and Zieli{\\'n}ski, Bartosz Micha{\\l} and Twardowski, Bart{\\l}omiej},\n  booktitle={The Twelfth International Conference on Learning Representations},\n  year={2023}\n}\n   ```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgrypesc%2Fseed","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgrypesc%2Fseed","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgrypesc%2Fseed/lists"}