Papers › Dissecting Self-Supervised Learning Methods for Surgical Computer Vision
Dissecting Self-Supervised Learning Methods for Surgical Computer Vision
Sanat Ramesh, Vinkle Srivastav, Deepak Alapatt, Tong Yu, Aditya Murali, Luca Sestini, Chinedu Innocent Nwoye, Idris Hamoud, Saurav Sharma, Antoine Fleurentin, Georgios Exarchakis, Alexandros Karargyris, Nicolas Padoy
The field of surgical computer vision has undergone considerable breakthroughs in recent years with the rising popularity of deep neural network-based methods. However, standard fully-supervised approaches for training such models require vast amounts of annotated data, imposing a prohibitively high cost; especially in the clinical domain. Self-Supervised Learning (SSL) methods, which have begun to gain traction in the general computer vision community, represent a potential solution to these annotation costs, allowing to learn useful representations from only unlabeled data. Still, the effectiveness of SSL methods in more complex and impactful domains, such as medicine and surgery, remains limited and unexplored. In this work, we address this critical need by investigating four state-of-the-art SSL methods (MoCo v2, SimCLR, DINO, SwAV) in the context of surgical computer vision. We present an extensive analysis of the performance of these methods on the Cholec80 dataset for two fundamental and popular tasks in surgical context understanding, phase recognition and tool presence detection. We examine their parameterization, then their behavior with respect to training data quantities in semi-supervised settings. Correct transfer of these methods to surgery, as described and conducted in this work, leads to substantial performance gains over generic uses of SSL - up to 7.4% on phase recognition and 20% on tool presence detection - as well as state-of-the-art semi-supervised phase recognition approaches by up to 14%. Further results obtained on a highly diverse selection of surgical datasets exhibit strong generalization properties. The code is available at https://github.com/CAMMA-public/SelfSupSurg.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Action Triplet Recognition | CholecT50 (Challenge) | MoCo V2 Surg SSL - Rendezvous head | mAP | 35.7 | #4 of 27 | Archive leaderboard | report |
| Semantic Segmentation | Endoscapes | MoCo V2 Surg SSL - DeepLabv3+ head | Mean F1 | 73.2 | #1 of 2 | Archive leaderboard | report |
| Surgical phase recognition | Cholec80 | MoCo V2 Surg SSL - TCN head | F1 | 81.6 | #4 of 6 | Archive leaderboard | report |
| Surgical phase recognition | HeiChole Benchmark | MoCo V2 Surg SSL - TCN head | F1 | 64.7 | #5 of 5 | Archive leaderboard | report |
| Surgical tool detection | Cholec80 | MoCo V2 Surg SSL - FCN head | mAP | 93.5 | #1 of 6 | Archive leaderboard | report |
| Surgical tool detection | HeiChole Benchmark | MoCo V2 Surg SSL - FCN head | mAP | 66.9 | #1 of 1 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections