# Exploring Pre-training Across Domains for Few-Shot Surgical Skill Assessment

arXiv: https://arxiv.org/abs/2509.09327 · HTML: https://mlsanity.com/paper/2509.09327/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 11 Sep 2025.

## Builds on (most cited first, 20 of 20)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [A Baseline for Few-Shot Image Classification](https://mlsanity.com/paper/1909.02729/) (2019)
- [Surgical Data Science: Enabling Next-Generation Surgery](https://mlsanity.com/paper/1701.06482/) (2017)
- [Surgical Data Science -- from Concepts toward Clinical Translation](https://mlsanity.com/paper/2011.02284/) (2020)
- [Learning from Few Examples: A Summary of Approaches to Few-Shot Learning](https://mlsanity.com/paper/2203.04291/) (2022)
- [Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train](https://mlsanity.com/paper/2306.16741/) (2023)
- [Video-based surgical skill assessment using 3D convolutional neural networks](https://mlsanity.com/paper/1903.02306/) (2019)
- [SAR-RARP50: Segmentation of surgical instrumentation and Action Recognition on Robot-Assisted Radical Prostatectomy Challenge](https://mlsanity.com/paper/2401.00496/) (2023)
- [Towards Unified Surgical Skill Assessment](https://mlsanity.com/paper/2106.01035/) (2021)
- [Dissecting Self-Supervised Learning Methods for Surgical Computer Vision](https://mlsanity.com/paper/2207.00449/) (2022)
- [Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty](https://mlsanity.com/paper/2202.01339/) (2022)
- [Surgical Skill Assessment via Video Semantic Aggregation](https://mlsanity.com/paper/2208.02611/) (2022)
- [Whether and When does Endoscopy Domain Pretraining Make Sense?](https://mlsanity.com/paper/2303.17636/) (2023)
- [Exploring the Effect of Dataset Diversity in Self-Supervised Learning for Surgical Computer Vision](https://mlsanity.com/paper/2407.17904/) (2024)
- [One-shot skill assessment in high-stakes domains with limited data via meta learning](https://mlsanity.com/paper/2301.00812/) (2022)

## Built on by (most cited first, 2 of 2)

- [CoRe-DA: Contrastive Regression for Unsupervised Domain Adaptation in Surgical Skill Assessment](https://mlsanity.com/paper/2603.29666/) (2026)
- [Looking Beyond the Scale: Do Surgical Skill Models Learn Transferable Representations Across Assessment Rubrics?](https://mlsanity.com/paper/2608.17519/) (2026)

## Abstract (arXiv)

Automated surgical skill assessment (SSA) is a central task in surgical computer vision. Developing robust SSA models is challenging due to the scarcity of skill annotations, which are time-consuming to produce and require expert consensus. Few-shot learning (FSL) offers a scalable alternative enabling model development with minimal supervision, though its success critically depends on effective pre-training. While widely studied for several surgical downstream tasks, pre-training has remained largely unexplored in SSA. In this work, we formulate SSA as a few-shot task and investigate how self-supervised pre-training strategies affect downstream few-shot SSA performance. We annotate a publicly available robotic surgery dataset with Objective Structured Assessment of Technical Skill (OSATS) scores, and evaluate various pre-training sources across three few-shot settings. We quantify domain similarity and analyze how domain gap and the inclusion of procedure-specific data into pre-training influence transferability. Our results show that small but domain-relevant datasets can outperform large scale, less aligned ones, achieving accuracies of 60.16%, 66.03%, and 73.65% in the 1-, 2-, and 5-shot settings, respectively. Moreover, incorporating procedure-specific data into pre-training with a domain-relevant external dataset significantly boosts downstream performance, with an average gain of +1.22% in accuracy and +2.28% in F1-score; however, applying the same strategy with less similar but large-scale sources can instead lead to performance degradation. Code and models are available at https://github.com/anastadimi/ssa-fsl.