SRA-Det：超越类别名称的全粒度开放词表检测
SRA-Det: Learning Omni-Grained Open-Vocabulary Detection Beyond Category Names
把开放词表检测从「类别名匹配」推进到「属性级细粒度查询」：用注意力从 token 级文本特征检索多个语义侧面，再用 soft-min 匹配近似可微的逻辑与，保证所有关键属性同时满足；这套「多侧面检索 + 软与匹配」可直接迁移到任何文本-区域对齐的检测/定位头。
原文依据 a soft-min matching rule that behaves like a differentiable logical AND over these facets
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论开放词表目标检测（OVD）旨在检测由任意文本描述的目标，但现有方法大多停留在粗粒度类别层面，难以处理细粒度、属性敏感的查询。本文从模型与数据两个角度解决该问题。我们提出语义检索增强检测器（SRA-Det），它使用基于注意力的模块从 token 级文本特征中检索多个语义侧面，并采用 soft-min 匹配规则，该规则在这些侧面上表现得如同可微的逻辑与，从而确保所有关键属性都得到满足。与此同时，我们引入一条自动属性增强数据流水线，利用大语言模型生成类别特定的视觉属性，并通过基于 CLIP 的双重相似度校验在实例层面验证这些属性。在 Swin-T 骨干网络下，我们的方法在 FG-OVD 的零样本设定下达到 54.9 平均精度均值，在 LVIS 上达到 40.4 AP，在细粒度与通用 OVD 性能上均表现强劲。
英文原文摘要 964 字符
Open-vocabulary object detection (OVD) aims to detect objects described by arbitrary text, but most existing methods operate at a coarse category level and struggle with fine-grained, attribute-sensitive queries. We address this from both model and data perspectives. We propose a Semantic-Retrieval-Augmented Detector (SRA-Det) that uses an attention-based module to retrieve multiple semantic facets from token-level text features, and a soft-min matching rule that behaves like a differentiable logical AND over these facets, ensuring that all key attributes are satisfied. In parallel, we introduce an automatic attribute-augmented data pipeline that uses an LLM to generate category-specific visual attributes and a dual CLIP-based similarity check to verify them at the instance level. With a Swin-T backbone, our approach achieves 54.9 mAP in the zero-shot setting on FG-OVD and 40.4 AP on LVIS, establishing strong fine-grained and general OVD performance.