# SurgPETL: Parameter-Efficient Image-to-Surgical-Video Transfer Learning for Surgical Phase Recognition

Source: [SurgPETL: Parameter-Efficient Image-to-Surgical-Video Transfer Learning for Surgical Phase Recognition](<https://www.sota2.com/research/paper/68fa75041e209131cea65483>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:24:17.272Z

Authors: Shu Yang, Zhiyuan Cai, Luyang Luo, Ning Ma, Shuchang Xu, Hao Chen

Published: 2024-09-30T08:33:50.000Z

## Abstract

Capitalizing on image-level pre-trained models for various downstream tasks has recently emerged with promising performance. However, the paradigm of "image pre-training followed by video fine-tuning" for high-dimensional video data inevitably poses significant performance bottlenecks. Furthermore, in the medical domain, many surgical video tasks encounter additional challenges posed by the limited availability of video data and the necessity for comprehensive spatial-temporal modeling. Recently, Parameter-Efficient Image-to-Video Transfer Learning has emerged as an efficient and effective paradigm for video action recognition tasks, which employs image-level pre-trained models with promising feature transferability and involves cross-modality temporal modeling with minimal fine-tuning. Nevertheless, the effectiveness and generalizability of this paradigm within intricate surgical domain remain unexplored. In this paper, we delve into a novel problem of efficiently adapting image-level pre-trained models to specialize in fine-grained surgical phase recognition, termed as Parameter-Efficient Image-to-Surgical-Video Transfer Learning. Firstly, we develop a parameter-efficient transfer learning benchmark SurgPETL for surgical phase recognition, and conduct extensive experiments with three advanced methods based on ViTs of two distinct scales pre-trained on five large-scale natural and medical datasets. Then, we introduce the Spatial-Temporal Adaptation module, integrating a standard spatial adapter with a novel temporal adapter to capture detailed spatial features and establish connections across temporal sequences for robust spatial-temporal modeling. Extensive experiments on three challenging datasets spanning various surgical procedures demonstrate the effectiveness of SurgPETL with STA.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Abdominal trauma detection on Proprietary abdominal ultrasound video dataset (test)](<https://www.sota2.com/research/sota/abdominal-trauma-detection-on-proprietary-abdominal-ultrasound-video-dataset-test.md>): Abdominal trauma detection; Proprietary abdominal ultrasound video dataset (test); Accuracy: 70.76.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2409.20083>)

[PDF](<https://arxiv.org/pdf/2409.20083.pdf>)
