YOLOv12-m — PitVis-2023 instrument recognition

Supervised YOLOv12-m detector trained for the 18 PitVis-2023 instruments, then scored as multi-label presence.

This is the “YOLOv12-m” row on the Instruments tab of the SDSC × Chicago Booth surgical video understanding leaderboard.

Evaluation

Full PitVis-2023 validation split (95% bootstrap CI):

Metric Value
Exact match 82.78% (82.36–83.20)
Micro-averaged F1 82.75% (82.32–83.20)

License note

Derived from Ultralytics YOLO weights; distributed under AGPL-3.0.

Limitations

Research baseline only. Not a medical device.

Downloads last month
11
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including skblv/yolov12m-pitvis-instruments