两篇新的研究论文介绍了用于推理分割的先进方法，这项任务涉及分割由复杂语言描述的对象。CR-Seg 利用带有思维链（CoT）机制的关注引导、粗略到精细的方法来提高定位和推理一致性。另一方面，Seg-Zero 采用认知强化学习来实现零样本泛化，并在没有监督推理数据的情况下推导出明确的推理链，在基准测试中表现优于以前的模型。 AI
影响 推理分割的这些进步可能为基于复杂语言的查询带来更直观、更准确的图像分析工具。
排序理由 两篇学术论文介绍了特定 AI 任务的新颖方法。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2606.03564v1 Announce Type: cross Abstract: Reasoning segmentation aims to segment target objects described by complex language through joint visual-textual reasoning. Existing methods typically rely on either learned semantic tokens to bridge Multimodal Large Language Mode…
Reasoning segmentation aims to segment target objects described by complex language through joint visual-textual reasoning. Existing methods typically rely on either learned semantic tokens to bridge Multimodal Large Language Models (MLLMs) and segmentation models, suffering from…
arXiv:2503.06520v3 Announce Type: replace Abstract: Traditional methods for reasoning segmentation rely on supervised fine-tuning with categorical labels and simple descriptions, limiting its out-of-domain generalization and lacking explicit reasoning processes. To address these …