# Generalizing Surgical Instruments Segmentation to Unseen Domains with One-to-Many Synthesis

arXiv: https://arxiv.org/abs/2306.16285 · HTML: https://mlsanity.com/paper/2306.16285/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 23 references that are in the map.
- First posted on arXiv 28 Jun 2023.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection](https://mlsanity.com/paper/1708.01642/) (2017)
- [2017 Robotic Instrument Segmentation Challenge](https://mlsanity.com/paper/1902.06426/) (2019)
- [2018 Robotic Scene Segmentation Challenge](https://mlsanity.com/paper/2001.11190/) (2020)
- [Surgical-VQA: Visual Question Answering in Surgical Scenes using Transformer](https://mlsanity.com/paper/2206.11053/) (2022)
- [Learning to Generate Synthetic Data via Compositing](https://mlsanity.com/paper/1904.05475/) (2019)
- [Learning and Reasoning with the Graph Structure Representation in Robotic Surgery](https://mlsanity.com/paper/2007.03357/) (2020)
- [Exploring Intra- and Inter-Video Relation for Surgical Semantic Scene Segmentation](https://mlsanity.com/paper/2203.15251/) (2022)
- [Synthetic and Real Inputs for Tool Segmentation in Robotic Surgery](https://mlsanity.com/paper/2007.09107/) (2020)
- [Image Compositing for Segmentation of Surgical Tools without Manual Annotations](https://mlsanity.com/paper/2102.09528/) (2021)
- [ST-MTL: Spatio-Temporal Multitask Learning Model to Predict Scanpath While Tracking Instruments in Robotic Surgery](https://mlsanity.com/paper/2112.08189/) (2021)
- [Class-Incremental Domain Adaptation with Smoothing and Calibration for Surgical Report Generation](https://mlsanity.com/paper/2107.11091/) (2021)
- [Learning Domain Adaptation with Model Calibration for Surgical Report Generation in Robotic Surgery](https://mlsanity.com/paper/2103.17120/) (2021)
- [Rethinking Surgical Instrument Segmentation: A Background Image Can Be All You Need](https://mlsanity.com/paper/2206.11804/) (2022)
- [Rethinking Surgical Captioning: End-to-End Window-Based MLP Transformer Using Patches](https://mlsanity.com/paper/2207.00113/) (2022)
- ["Train one, Classify one, Teach one" -- Cross-surgery transfer learning for surgical step recognition](https://mlsanity.com/paper/2102.12308/) (2021)

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

- [SegCol Challenge: Semantic Segmentation for Tools and Fold Edges in Colonoscopy data](https://mlsanity.com/paper/2412.16078/) (2024)
- [CataractSAM-2: A Domain-Adapted Model for Anterior Segment Surgery Segmentation and Scalable Ground-Truth Annotation](https://mlsanity.com/paper/2603.21566/) (2026)

## Abstract (arXiv)

Despite their impressive performance in various surgical scene understanding tasks, deep learning-based methods are frequently hindered from deploying to real-world surgical applications for various causes. Particularly, data collection, annotation, and domain shift in-between sites and patients are the most common obstacles. In this work, we mitigate data-related issues by efficiently leveraging minimal source images to generate synthetic surgical instrument segmentation datasets and achieve outstanding generalization performance on unseen real domains. Specifically, in our framework, only one background tissue image and at most three images of each foreground instrument are taken as the seed images. These source images are extensively transformed and employed to build up the foreground and background image pools, from which randomly sampled tissue and instrument images are composed with multiple blending techniques to generate new surgical scene images. Besides, we introduce hybrid training-time augmentations to diversify the training data further. Extensive evaluation on three real-world datasets, i.e., Endo2017, Endo2018, and RoboTool, demonstrates that our one-to-many synthetic surgical instruments datasets generation and segmentation framework can achieve encouraging performance compared with training with real data. Notably, on the RoboTool dataset, where a more significant domain gap exists, our framework shows its superiority of generalization by a considerable margin. We expect that our inspiring results will attract research attention to improving model generalization with data synthesizing.