Unsupervised Domain-Adaptive Semantic Segmentation for Surgical Instruments Leveraging Dropout-Enhanced Dual Heads and Coarse-Grained Classification Branch

Abstract

Accurate semantic segmentation for surgical instruments is crucial in robot-assisted minimally invasive surgery, mainly regarded as a core module in surgical-instrument tracking and operation guidance. Nevertheless, it is usually difficult for existing semantic surgical-instrument segmentation approaches to adapt to unknown surgical scenes, particularly due to their insufficient consideration for reducing the domain gaps across different scenes. To address this issue, we propose an unsupervised domain-adaptive semantic segmentation approach for surgical instruments, leveraging Dropout-enhanced Dual Heads and Coarse-Grained classification branch (D2HCG). The proposed approach comprises dropout-enhanced dual heads for diverse feature representation, and a coarse-grained classification branch for capturing complexities across varying granularities. This incorporates consistency loss functions targeting fine-grained features and coarse-grained granularities, aiming to reduce cross-scene domain gaps. Afterwards, we perform experiments in cross-scene surgical-instrument semantic segmentation cases, with the experimental results reporting the effectiveness for the proposed approach, compared with state-of-the-art semantic segmentation ones.