用强化学习让视频分割模型一步步推理，更准且可解释。
ReVSeg: Incentivizing the Reasoning Chain for Video Segmentation with Reinforcement Learning
- 将分割过程拆解为语义理解、时序证据选择、空间定位三步决策
- 在多个基准上达到顶尖性能，推理路径清晰可追踪
- 适合需要透明决策过程的视频分析场景
以推理为核心的视频对象分割任务极具挑战：查询常涉及动态变化、因果关系和时间交互，而非静态外观。现有方法通常将这些因素简化为隐式嵌入，导致推理链模糊且难以处理。为此，我们采用显式分解视角，提出ReVSeg，通过预训练视觉语言模型（VLMs）的原生接口执行序列化决策。ReVSeg不依赖单步预测，而是分三步执行——语义理解、时序证据选择、空间定位，与预训练能力对齐。同时，利用强化学习优化多步推理链，使模型能从结果反馈中自我提升决策质量。实验表明，ReVSeg在标准视频对象分割基准上达到最先进性能，并生成可解释的推理轨迹。
原文摘要 · Abstract (English)
Reasoning-centric video object segmentation is an inherently complex task: the query often refers to dynamics, causality, and temporal interactions, rather than static appearances. Yet existing solutions generally collapse these factors into simplified reasoning with latent embeddings, rendering the reasoning chain opaque and essentially intractable. We therefore adopt an explicit decomposition perspective and introduce ReVSeg, which executes reasoning as sequential decisions in the native interface of pretrained vision language models (VLMs). Rather than folding all reasoning into a single-step prediction, ReVSeg executes three explicit operations -- semantics interpretation, temporal evidence selection, and spatial grounding -- aligning pretrained capabilities. We further employ reinforcement learning to optimize the multi-step reasoning chain, enabling the model to self-refine its decision quality from outcome-driven signals. Experimental results demonstrate that ReVSeg attains state-of-the-art performances on standard video object segmentation benchmarks and yields interpretable reasoning trajectories. Project page is available at https://clementine24.github.io/ReVSeg/ .
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。