Bridging Granularity Gaps: Hierarchical Semantic Learning for Cross-domain Few-shot Segmentation

TL;DR

This paper introduces a Hierarchical Semantic Learning framework for cross-domain few-shot segmentation, addressing segmentation granularity gaps with novel modules to improve semantic discriminability across diverse domains.

Contribution

The paper proposes a new HSL framework with DSR, HSM, and PCMT modules to enhance hierarchical semantic feature learning and segmentation accuracy in cross-domain few-shot tasks.

Findings

Achieves state-of-the-art results on four target domain datasets.

Effectively models hierarchical semantics to improve segmentation.

Demonstrates robustness to style and granularity gaps.

Abstract

Cross-domain Few-shot Segmentation (CD-FSS) aims to segment novel classes from target domains that are not involved in training and have significantly different data distributions from the source domain, using only a few annotated samples, and recent years have witnessed significant progress on this task. However, existing CD-FSS methods primarily focus on style gaps between source and target domains while ignoring segmentation granularity gaps, resulting in insufficient semantic discriminability for novel classes in target domains. Therefore, we propose a Hierarchical Semantic Learning (HSL) framework to tackle this problem. Specifically, we introduce a Dual Style Randomization (DSR) module and a Hierarchical Semantic Mining (HSM) module to learn hierarchical semantic features, thereby enhancing the model's ability to recognize semantics at varying granularities. DSR simulates target domain data with diverse foreground-background style differences and overall style variations through foreground and global style randomization respectively, while HSM leverages multi-scale superpixels to guide the model to mine intra-class consistency and inter-class distinction at different granularities. Additionally, we also propose a Prototype Confidence-modulated Thresholding (PCMT) module to mitigate segmentation ambiguity when foreground and background are excessively similar. Extensive experiments are conducted on four popular target domain datasets, and the results demonstrate that our method achieves state-of-the-art performance.