提出分阶段推理分割框架，解决多模态大模型过思考问题。
DR$^2$Seg: Decomposed Two-Stage Rollouts for Efficient Reasoning Segmentation in Multimodal Large Language Models
- 分两阶段：先生成目标对象自包含描述，再用描述验证定位
- 在Qwen2.5-VL和SAM2/3上提升推理效率与分割准确率
- 无需额外监督，通过自奖励机制减少注意力分散
推理分割是新兴的视觉语言任务，需对复杂文本查询进行推理以精确分割物体。现有方法常出现过思考现象，生成冗长推理链，干扰物体定位。为此，我们提出DR$^2$Seg，一种无需额外思维监督的自奖励框架，同时提升推理效率与分割精度。该方法采用两阶段展开策略，将推理分割分解为多模态推理与指代分割。第一阶段，模型生成明确指定目标物体的自包含描述；第二阶段，用此描述替代原复杂查询进行验证。基于此设计，引入两个自奖励机制，缓解过思考及注意力分散问题。在Qwen2.5-VL的3B与7B版本，以及SAM2和SAM3上开展的大量实验表明，DR$^2$Seg始终提升推理效率与整体分割准确率。
原文摘要 · Abstract (English)
Reasoning segmentation is an emerging vision-language task that requires reasoning over intricate text queries to precisely segment objects. However, existing methods typically suffer from overthinking, generating verbose reasoning chains that interfere with object localization in multimodal large language models (MLLMs). To address this issue, we propose DR$^2$Seg, a self-rewarding framework that improves both reasoning efficiency and segmentation accuracy without requiring extra thinking supervision. DR$^2$Seg employs a two-stage rollout strategy that decomposes reasoning segmentation into multimodal reasoning and referring segmentation. In the first stage, the model generates a self-contained description that explicitly specifies the target object. In the second stage, this description replaces the original complex query to verify its self-containment. Based on this design, two self-rewards are introduced to mitigate overthinking and the associated attention dispersion. Extensive experiments conducted on 3B and 7B variants of Qwen2.5-VL, as well as on both SAM2 and SAM3, demonstrate that DR$^2$Seg consistently improves reasoning efficiency and overall segmentation accuracy.
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。