Surgical video understanding baselines
Collection
LoRA adapters, supervised CNN baselines, and LemonFM linear probes trained for the SDSC x Chicago Booth surgical video understanding leaderboard. • 16 items • Updated
ResNet-50 — CholecT50 verb recognition
Supervised 10-way multi-label ResNet-50 baseline for current-action (verb) recognition on CholecT50 frames.
Trained as a baseline for the SDSC × Chicago Booth surgical video understanding leaderboard (Recommendations tab).
Evaluation
Full 19,923-frame validation split (95% bootstrap CI):
| Metric | Value |
|---|---|
| Exact match | 52.9% (52.3–53.6) |
| Micro-averaged F1 | 75.2% (74.8–75.6) |
Limitations
Research baseline only. Not a medical device.