{"id":13709060,"url":"https://github.com/VILA-Lab/i-mae","last_synced_at":"2025-05-06T15:32:07.377Z","repository":{"id":177277054,"uuid":"554977816","full_name":"VILA-Lab/i-mae","owner":"VILA-Lab","description":"i-mae Pytorch Repo","archived":false,"fork":false,"pushed_at":"2024-04-06T15:05:18.000Z","size":39,"stargazers_count":20,"open_issues_count":2,"forks_count":3,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-04-18T21:19:10.754Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/VILA-Lab.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,"dei":null}},"created_at":"2022-10-20T18:28:51.000Z","updated_at":"2025-03-15T05:05:43.000Z","dependencies_parsed_at":"2023-07-20T03:15:09.984Z","dependency_job_id":null,"html_url":"https://github.com/VILA-Lab/i-mae","commit_stats":null,"previous_names":["vila-lab/i-mae"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VILA-Lab%2Fi-mae","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VILA-Lab%2Fi-mae/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VILA-Lab%2Fi-mae/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VILA-Lab%2Fi-mae/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/VILA-Lab","download_url":"https://codeload.github.com/VILA-Lab/i-mae/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252713012,"owners_count":21792409,"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":[],"created_at":"2024-08-02T23:00:35.545Z","updated_at":"2025-05-06T15:32:02.368Z","avatar_url":"https://github.com/VILA-Lab.png","language":"Python","funding_links":[],"categories":["Mixup for Self-supervised Learning"],"sub_categories":["Label Mixup Methods"],"readme":"# A PyTorch Implementation of i-MAE: Linearly Separable Representation in MAE\n\n[Kevin Zhang*](https://kzyz.netlify.com/), [Zhiqiang Shen*](http://zhiqiangshen.com/)\n\n[`Project Page`](https://zhiqiangshen.com/projects/i-mae/)\n| [`Paper`](https://arxiv.org/abs/2210.11470)\n| [`BibTeX`](#citation)\n\n[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/vision-learning-acceleration-lab/i-mae/blob/main/i-MAE_demo.ipynb)\n\n![i-MAE2](https://user-images.githubusercontent.com/52997677/196735725-496592d3-5883-4db4-ba34-04d0a8dab535.svg)\n\nWe provide a PyTorch/GPU based implementation of our technical report [i-MAE: Are Latent Representations in Masked Autoencoders Linearly Separable?\n](https://arxiv.org/abs/2210.11470)\n\n### Catalog\n\n- [X] Pretrain demo with Colab\n- [X] Pre-training and Fine-tuning code\n- [ ] Weights Upload\n\n### Pre-training\n\nThe pre-training instruction is in [PRETRAIN.md](https://github.com/facebookresearch/mae/blob/main/PRETRAIN.md).\n\n### Fine-tuning\n\nThe fine-tuning instruction is in [FINETUNE.md](https://github.com/facebookresearch/mae/blob/main/FINETUNE.md).\n\n### Visualization demo\n\nPlease visit our interactive demo on our [website](https://zhiqiangshen.com/projects/i-mae/), or run our visualization demo with a [Colab notebook](https://colab.research.google.com/github/vision-learning-acceleration-lab/i-mae/blob/main/i-MAE_demo.ipynb) [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/vision-learning-acceleration-lab/i-mae/blob/main/i-MAE_demo.ipynb)\n\n### Acknowledgement\n\nThis repository is based on [timm](https://github.com/rwightman/pytorch-image-models/tree/master/timm) and [MAE](https://github.com/facebookresearch/mae) repositories.\n\n### License\n\nThis project is under the CC-BY-NC 4.0 license. See [LICENSE](LICENSE) for details.\n\n### Citation\n\nIf you find this repository helpful, please consider citing our work:\n\n```\n@article{zhang2022i-mae,\n  title={i-MAE: Are Latent Representations in Masked Autoencoders Linearly Separable?},\n  author = {Zhang, Kevin and Shen, Zhiqiang},\n  journal={arXiv preprint arXiv:2210.11470},\n  year={2022}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FVILA-Lab%2Fi-mae","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FVILA-Lab%2Fi-mae","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FVILA-Lab%2Fi-mae/lists"}