ymxlzgy / FoundAD
[ICLR 2026] The implementation of the paper Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors
Why this job: topics: computer-vision, foundation-models, machine-learning
What it does
The implementation of the paper Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors (arXiv, OpenReview).
Get started
python foundad/main.py mode=demo app=test testing.segmentation_vis=True data.dataset=mvtec data.data_name=mvtec_1shot data.test_root=assets/mvtec - Maintenance
- Active
- Last commit 2 months ago
- Stars
- 108
- +1 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 44% closed
- 5 still open
- Pull requests
- 1 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| Biohub / VisCy | 108 | 7 days ago | BSD-3-Clause | No downloads |
More: languages, topics and project record
Languages
- Python 100%
- Makefile <1%
Topics
- anomaly-detection
- anomaly-detection-algorithm
- anomaly-localization
- anomaly-segmentation
- anomalydetection
- clip
- computer-vision
- dinov2
- dinov3
- few-shot-anomaly-detection
- few-shot-learning
- foundation-models
Project record
- JobAI libraries and models
- StatusListed
- Commits35
- Forks11
- Watching1
- Stars in 28 days+20
- CreatedAug 15, 2025
- First seen by usNov 7, 2026
- CheckedNov 8, 2026