LAION-AI / LAION-AI/CLIP_benchmark
Implement LP++ for better linear probing results
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 815
- Forks
- 102
- PR merge metrics
- No merged PRs in 30d
Description
Implement "lp++: A Surprisingly Strong Linear Probe for Few-Shot CLIP" (https://openaccess.thecvf.com/content/CVPR2024/papers/Huang_LP_A_Surprisingly_Strong_Linear_Probe_for_Few-Shot_CLIP_CVPR_2024_paper.pdf), a strong linear probing baseline
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 CVPR 2024 paper, “LP++: A Surprisingly Strong Linear Probe for Few-Shot CLIP,” to understand the proposed baseline. The issue does not identify files, tests, or entry points; done means LP++ is implemented as a usable linear-probing baseline in CLIP_benchmark.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100