Generalizing Surgical Instruments Segmentation to Unseen Domains with One-to-Many Synthesis
An Wang,Mobarakol Islam,Mengya Xu,Hongliang Ren,An Wang,Mobarakol Islam,Mengya Xu,Hongliang Ren
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 ...
