DARNet: Bridging Domain Gaps in Cross-Domain Few-Shot Segmentation with Dynamic Adaptation

TL;DR

DARNet introduces dynamic adaptation techniques, including feature perturbation and self-matching, to improve cross-domain few-shot segmentation by enhancing generalization and domain-specific refinement.

Contribution

The paper proposes DARNet, a novel method with CSD, ARSM, and TTA strategies to address domain discrepancies in cross-domain few-shot segmentation.

Findings

Outperforms state-of-the-art in CD-FSS tasks

Effective domain generalization through feature perturbation

Improved accuracy via dynamic self-matching and test-time adaptation

Abstract

Few-shot segmentation (FSS) aims to segment novel classes in a query image by using only a small number of supporting images from base classes. However, in cross-domain few-shot segmentation (CD-FSS), leveraging features from label-rich domains for resource-constrained domains poses challenges due to domain discrepancies. This work presents a Dynamically Adaptive Refine (DARNet) method that aims to balance generalization and specificity for CD-FSS. Our method includes the Channel Statistics Disruption (CSD) strategy, which perturbs feature channel statistics in the source domain, bolstering generalization to unknown target domains. Moreover, recognizing the variability across target domains, an Adaptive Refine Self-Matching (ARSM) method is also proposed to adjust the matching threshold and dynamically refine the prediction result with the self-matching method, enhancing accuracy. We also present a Test-Time Adaptation (TTA) method to refine the model's adaptability to diverse feature distributions. Our approach demonstrates superior performance against state-of-the-art methods in CD-FSS tasks.