Dual-Agent Optimization framework for Cross-Domain Few-Shot Segmentation

2025-01-01 · CVPR 2025 1 · Zhaoyang Li, YuAn Wang, Wangkai Li, Tianzhu Zhang, Xiang Liu

Cross-Domain Few-Shot Segmentation (CD-FSS) extends the generalization ability of Few-Shot Segmentation (FSS) beyond a single domain, enabling more practical applications. However, directly employing conventional FSS methods suffers from severe performance degradation in cross-domain settings, primarily due to feature sensitivity and support-to-query matching process sensitivity across domains. Existing methods for CD-FSS either focus on domain adaptation of features or delve into designing matching strategies for enhanced cross-domain robustness. Nonetheless, they overlook the fact that these two issues are interdependent and should be addressed jointly. In this work, we tackle these two issues within a unified framework by optimizing features in the frequency domain and enhancing the matching process in the spatial domain, working jointly to handle the deviations introduced by the domain gap. To this end, we propose a coherent Dual-Agent Optimization (DATO) framework, including a consistent mutual aggregation (CMA) and a correlation rectification strategy (CRS). In the consistent mutual aggregation module, we employ a set of agents to learn domain-invariant features across domains, and then use these features to enhance the original representations for feature adaptation. In the correlation rectification strategy, the agent-aggregated domain-invariant features serve as a bridge, transforming the support-to-query matching process into a referable feature space and reducing its domain sensitivity. Extensive experiments demonstrate the efficacy of our approach.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Cross-Domain Few-Shot Domain AdaptationSensitivity

Methods 이 논문이 사용한 방법론

Focus 설명 없음

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

MASCOT: Towards Multi-Agent Socio-Collaborative Companion Systems

2026-01-20 · Yiyang Wang, Yiqiao Jin, Alex Cabral, Josiah Hester arxiv

Multi-agent systems (MAS) are emerging as promising socio-collaborative companions for emotional and cognitive support. However, existing systems frequently suffer from persona collapse, where agents revert to generic, h…

CAPO: Constraint-Aware Prompt Optimization for LLM Agents

2026-08-17 · Victor Ye Dong, Reid Pryzant, Yi Liu, Jian Jiao arxiv

Large language models (LLMs) are increasingly deployed as agents that rely on system prompts to use tools and complete tasks. Such deployments impose distinct operational requirements, including appropriate tool use, con…

A Multi-Agent Framework with Automated Decision Rule Optimization for Cross-Domain Misinformation Detection

2025-03-30 · Hui Li, Ante Wang, kunquan li, Zhihao Wang 외

Misinformation spans various domains, but detection methods trained on specific domains often perform poorly when applied to others. With the rapid development of Large Language Models (LLMs), researchers have begun to u…

Misinformation

SOLID: a Framework of Synergizing Optimization and LLMs for Intelligent Decision-Making

2025-11-19 · Yinsheng Wang, Tario G You, Léonard Boussioux, Shan Liu arxiv

This paper introduces SOLID (Synergizing Optimization and Large Language Models for Intelligent Decision-Making), a novel framework that integrates mathematical optimization with the contextual capabilities of large lang…

MAT-Agent: Adaptive Multi-Agent Training Optimization

2025-10-10 · Jusheng Zhang, Kaitong Cai, Yijia Fan, Ningyuan Liu 외 arxiv

Multi-label image classification demands adaptive training strategies to navigate complex, evolving visual-semantic landscapes, yet conventional methods rely on static configurations that falter in dynamic settings. We p…

Multi-Label Image Classification Domain Generalization Data Augmentation