让模型通过描述目标来聚焦关键区域，提升分割推理的准确性与效率
Discriminative Perception via Anchored Description for Reasoning Segmentation
- 引入描述性标题对比机制，区分目标与上下文
- 推理链长度减少约42%，ReasonSeg的cIoU提升3.09%
- 适合需要精准推理和可解释性的视觉语言任务
推理分割越来越多地使用强化学习生成解释性推理链，引导多模态大语言模型。然而，这些几何奖励主要局限于指导最终定位，无法判断推理过程是否仍锚定在目标区域，还是偏离到无关上下文。缺乏这种判别性引导，模型的推理常变得散漫冗长，难以在复杂场景中准确识别目标。因此，亟需补充判别感知能力，主动区分目标与背景。为此，我们提出DPAD，强制模型生成对目标对象的描述性标题，并通过对比该标题与目标区域及整体上下文的语义相关性，实现显式判别。优化此判别能力迫使模型关注目标的独特属性，形成更收敛高效的推理链。描述性标题同时作为可解释性依据，与分割结果对齐。在基准测试中验证了方法有效性，ReasonSeg的cIoU提升3.09%，推理链长度下降约42%。
原文摘要 · Abstract (English)
Reasoning segmentation increasingly employs reinforcement learning to generate explanatory reasoning chains that guide Multimodal Large Language Models. While these geometric rewards are primarily confined to guiding the final localization, they are incapable of discriminating whether the reasoning process remains anchored on the referred region or strays into irrelevant context. Lacking this discriminative guidance, the model's reasoning often devolves into unfocused and verbose chains that ultimately fail to disambiguate and perceive the target in complex scenes. This suggests a need to complement the RL objective with Discriminative Perception, an ability to actively distinguish a target from its context. To realize this, we propose DPAD to compel the model to generate a descriptive caption of the referred object, which is then used to explicitly discriminate by contrasting the caption's semantic relevance to the referred object against the wider context. By optimizing for this discriminative capability, the model is forced to focus on the unique attributes of the target, leading to a more converged and efficient reasoning chain. The descriptive caption also serves as an interpretability rationale that aligns with the segmentation. Experiments on the benchmarks confirm the validity of our approach, delivering substantial performance gains, with the cIoU on ReasonSeg increasing by 3.09% and the reasoning chain length decreasing by approximately 42%. Code is available at https://github.com/mrazhou/DPAD
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。