Bridging Granularity Gaps: Hierarchical Semantic Learning for Cross-domain Few-shot Segmentation
Sujun Sun, Haowen Gu, Cheng Xie, Yanxu Ren, Mingwu Ren, Haofeng Zhang
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
BibTeX
@inproceedings{aaai2026_bridginggranular,
title = {Bridging Granularity Gaps: Hierarchical Semantic Learning for Cross-domain Few-shot Segmentation},
author = {Sujun Sun and Haowen Gu and Cheng Xie and Yanxu Ren and Mingwu Ren and Haofeng Zhang},
booktitle = {AAAI 2026},
year = {2026}
}