Divide-and-Conquer Decoupled Network for Cross-Domain Few-Shot Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cong, Runmin, Wang, Anpeng, Wan, Bin, Zhang, Cong, Zhou, Xiaofei, Zhang, Wei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918398687969280
author Cong, Runmin
Wang, Anpeng
Wan, Bin
Zhang, Cong
Zhou, Xiaofei
Zhang, Wei
author_facet Cong, Runmin
Wang, Anpeng
Wan, Bin
Zhang, Cong
Zhou, Xiaofei
Zhang, Wei
contents Cross-domain few-shot segmentation (CD-FSS) aims to tackle the dual challenge of recognizing novel classes and adapting to unseen domains with limited annotations. However, encoder features often entangle domain-relevant and category-relevant information, limiting both generalization and rapid adaptation to new domains. To address this issue, we propose a Divide-and-Conquer Decoupled Network (DCDNet). In the training stage, to tackle feature entanglement that impedes cross-domain generalization and rapid adaptation, we propose the Adversarial-Contrastive Feature Decomposition (ACFD) module. It decouples backbone features into category-relevant private and domain-relevant shared representations via contrastive learning and adversarial learning. Then, to mitigate the potential degradation caused by the disentanglement, the Matrix-Guided Dynamic Fusion (MGDF) module adaptively integrates base, shared, and private features under spatial guidance, maintaining structural coherence. In addition, in the fine-tuning stage, to enhanced model generalization, the Cross-Adaptive Modulation (CAM) module is placed before the MGDF, where shared features guide private features via modulation ensuring effective integration of domain-relevant information. Extensive experiments on four challenging datasets show that DCDNet outperforms existing CD-FSS methods, setting a new state-of-the-art for cross-domain generalization and few-shot adaptation.
format Preprint
id arxiv_https___arxiv_org_abs_2511_07798
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Divide-and-Conquer Decoupled Network for Cross-Domain Few-Shot Segmentation
Cong, Runmin
Wang, Anpeng
Wan, Bin
Zhang, Cong
Zhou, Xiaofei
Zhang, Wei
Computer Vision and Pattern Recognition
Cross-domain few-shot segmentation (CD-FSS) aims to tackle the dual challenge of recognizing novel classes and adapting to unseen domains with limited annotations. However, encoder features often entangle domain-relevant and category-relevant information, limiting both generalization and rapid adaptation to new domains. To address this issue, we propose a Divide-and-Conquer Decoupled Network (DCDNet). In the training stage, to tackle feature entanglement that impedes cross-domain generalization and rapid adaptation, we propose the Adversarial-Contrastive Feature Decomposition (ACFD) module. It decouples backbone features into category-relevant private and domain-relevant shared representations via contrastive learning and adversarial learning. Then, to mitigate the potential degradation caused by the disentanglement, the Matrix-Guided Dynamic Fusion (MGDF) module adaptively integrates base, shared, and private features under spatial guidance, maintaining structural coherence. In addition, in the fine-tuning stage, to enhanced model generalization, the Cross-Adaptive Modulation (CAM) module is placed before the MGDF, where shared features guide private features via modulation ensuring effective integration of domain-relevant information. Extensive experiments on four challenging datasets show that DCDNet outperforms existing CD-FSS methods, setting a new state-of-the-art for cross-domain generalization and few-shot adaptation.
title Divide-and-Conquer Decoupled Network for Cross-Domain Few-Shot Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.07798