arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.03595cs.CV
收藏

Refer-Agent:一种具有推理和反思的协作多智能体系统用于指引用视频对象分割

Refer-Agent: A Collaborative Multi-Agent System with Reasoning and Reflection for Referring Video Object Segmentation

Sun Yat-sen University(中山大学)

Haichao Jiang, Tianming Liang, Wei-Shi Zheng, Jian-Fang Hu

AI总结:

Refer-Agent通过协作多智能体系统结合推理与反思机制,提升指引用视频对象分割的性能与灵活性。

摘要:

指引用视频对象分割(RVOS)旨在基于文本查询对视频中的对象进行分割。当前方法主要依赖于多模态大语言模型(MLLMs)的大规模监督微调(SFT)。然而,这种范式存在对大量数据的依赖以及在MLLMs快速演变时的可扩展性受限。尽管最近的零样本方法提供了一种灵活的替代方案,但其性能仍然显著落后于基于SFT的方法,原因是简单的流程设计。为了解决这些限制,我们提出了Refer-Agent,一种具有交替推理-反思机制的协作多智能体系统。该系统将RVOS分解为逐步推理过程。在推理过程中,我们引入了从粗到细的帧选择策略,以确保帧的多样性和文本相关性,同时提出了动态聚焦布局,可自适应调整智能体的视觉聚焦。此外,我们提出了一种反思链机制,该机制采用提问者-回答者对生成自我反思链,使系统能够验证中间结果并为下一步推理细化生成反馈。在五个具有挑战性的基准测试中,大量实验表明,Refer-Agent显著优于最先进的方法,包括基于SFT的模型和零样本方法。此外,Refer-Agent具有灵活性,并且可以在不增加任何额外微调成本的情况下快速集成新的MLLMs。代码将在https://github.com/iSEE-Laboratory/Refer-Agent上发布。

英文摘要:

Referring Video Object Segmentation (RVOS) aims to segment objects in videos based on textual queries. Current methods mainly rely on large-scale supervised fine-tuning (SFT) of Multi-modal Large Language Models (MLLMs). However, this paradigm suffers from heavy data dependence and limited scalability against the rapid evolution of MLLMs. Although recent zero-shot approaches offer a flexible alternative, their performance remains significantly behind SFT-based methods, due to the straightforward workflow designs. To address these limitations, we propose \textbf{Refer-Agent}, a collaborative multi-agent system with alternating reasoning-reflection mechanisms. This system decomposes RVOS into step-by-step reasoning process. During reasoning, we introduce a Coarse-to-Fine frame selection strategy to ensure the frame diversity and textual relevance, along with a Dynamic Focus Layout that adaptively adjusts the agent's visual focus. Furthermore, we propose a Chain-of-Reflection mechanism, which employs a Questioner-Responder pair to generate a self-reflection chain, enabling the system to verify intermediate results and generates feedback for next-round reasoning refinement. Extensive experiments on five challenging benchmarks demonstrate that Refer-Agent significantly outperforms state-of-the-art methods, including both SFT-based models and zero-shot approaches. Moreover, Refer-Agent is flexible and enables fast integration of new MLLMs without any additional fine-tuning costs. Code will be released at https://github.com/iSEE-Laboratory/Refer-Agent.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑