lightly-ai / lightly-ai/lightly-train
[FEAT] Support for MAE backbone for semantic segmentation
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.7k
- Forks
- 116
- Avg merge
- 2d 21h
- Merged PRs (30d)
- 6
Description
Hello Team,
First and foremost, thank you for your incredible work.
I'm writing to inquire about the roadmap and any potential plans for applying these powerful **MAE pre-trained** models to downstream dense prediction tasks, specifically **semantic segmentation**.
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
The issue requests support for using MAE-pretrained models for semantic segmentation, but it names no files, tests, entry points, or acceptance criteria. Start by locating the existing model and semantic-segmentation training paths, then define the required integration and validation before implementation. Done should include working MAE-backbone support and evidence that semantic segmentation training works.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100