resnet50-sarrarp50-gesture

skblv/resnet50-sarrarp50-gesture

resnet50-sarrarp50-gesture is a image classification model from skblv. Use it when you need a label for an image. It is set up for pytorch. The card lists the license as apache-2.0.

Supervised 8-way ResNet-50 baseline for suturing-gesture recognition on SAR-RARP50.

Downloads · 30 days

Access

Public

Updated Aug 31, 2026

Repo size

94.4 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.pt94.4 MB · 100%

At a glance

Task: Image Classification
Library: pytorch
License: apache-2.0
Access: Public
Created: Aug 28, 2026
Updated: Aug 31, 2026
SHA: af2b354b

Model card

From the Hugging Face model README

ResNet-50 — SAR-RARP50 suturing gestures

Supervised 8-way ResNet-50 baseline for suturing-gesture recognition on SAR-RARP50.

Trained as a baseline for the SDSC × Chicago Booth surgical video understanding leaderboard (Skill assessment tab).

Prompt example

This closed-set example mirrors the leaderboard format, not a text-input API for this checkpoint.

[surgical frame]

What suturing action is being performed in this frame?
Choose one label.

- Other
- Picking Up The Needle
- Positioning The Needle Tip
- Pushing The Needle Through The Tissue
- Pulling The Needle Out Of The Tissue
- Tying A Knot
- Cutting The Suture
- Returning Or Dropping The Needle

Evaluation

Full 636-frame validation split (95% bootstrap CI):

Metric	Value
Exact match	53.0% (49.2–57.1)

References

Skobelev, K., Fithian, E., Baranovski, Y., et al. A Comparative Study in Surgical AI: Potential and Limitations of Data, Compute, and Scaling. arXiv:2603.27341, 2026.
Dataset: Psychogyios, D., Colleoni, E., Van Amsterdam, B., et al. SAR-RARP50: Segmentation of surgical instrumentation and Action Recognition on Robot-Assisted Radical Prostatectomy Challenge. arXiv:2401.00496, 2024.

Limitations

Research baseline only. Not a medical device.

Task: Image Classification
Library: pytorch
License: apache-2.0
Created: Aug 28, 2026
Updated: Aug 31, 2026