lightly-ai / lightly-ai/lightly
MultiMAE: Multi-modal Multi-task Masked Autoencoders
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.8k
- Forks
- 367
- Avg merge
- 3d 22h
- Merged PRs (30d)
- 5
Description
Suggestion to include MultiMAE in lightly.
- Paper: https://doi.org/10.48550/arXiv.2204.01678
- Github repo: https://github.com/EPFL-VILAB/MultiMAE
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading the linked MultiMAE paper and GitHub repository, then inspect lightly's existing self-supervised learning and computer-vision entry points. The issue names no project files, tests, or specific integration scope; done would require a decided implementation plan and working MultiMAE support in lightly.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100