AI 中文总结
针对现有目标检测仅聚焦以事物为中心的实例、忽略关键场景元素的问题，本文提出ECAD设置，构建BTCO-Bench基准，设计ECADet检测器并引入GAER与PGQM模块，实验验证其在BTCO-Bench上的性能优势。
AI 中文摘要
目标检测是视觉感知的基础任务，为识别、 grounding、推理和交互提供结构化的区域表示。然而，现有检测范式大多继承了以事物为中心的对象性概念，检测器主要被训练用于定位离散且可计数的目标实例。因此，许多语义上有意义的视觉元素，如天空、道路、草地、水域和运动场，尽管对场景理解和空间推理至关重要，却常被归为背景。本文中，我们提出了扩展类无关检测（Expanded Class-Agnostic Detection, ECAD），这是一种旨在发现传统以事物为中心的对象之外的类别无关视觉候选的新设置。为支持该设置，我们构建了BTCO-Bench（Beyond Thing-Centric Objectness）基准，其包含类别无关的框标注，覆盖真实世界和跨域场景。我们进一步提出了ECADet，一种基于冻结DINOv3编码器的轻量DETR检测器，并引入几何感知专家回归（Geometry-Aware Expert Regression, GAER）和原型引导查询调制（Prototype-Guided Query Modulation, PGQM），分别用于改善各类视觉元素的定位和对象性估计。大量实验表明，ECADet在BTCO-Bench上始终优于代表性的类无关检测器和基于提议的检测器，证明了扩展对象性发现的有效性。代码和基准将被发布。
英文摘要
Object detection is a fundamental task in visual perception, providing structured region representations for recognition, grounding, reasoning, and interaction. However, existing detection paradigms largely inherit a thing-centric notion of objectness, where detectors are mainly trained to localize discrete and countable object instances. Consequently, many semantically meaningful visual elements, such as sky, road, grassland, water, and sports courts, are often absorbed into the background despite their importance for scene understanding and spatial reasoning. In this paper, we formulate Expanded Class-Agnostic Detection (ECAD), a new setting that aims to discover category-agnostic visual candidates beyond conventional thing-centric objects. To support this setting, we construct BTCO-Bench, a Beyond Thing-Centric Objectness benchmark with category-agnostic box annotations covering both real-world and cross-domain scenarios. We further propose ECADet, a lightweight DETR-based detector built upon a frozen DINOv3 encoder, and introduce Geometry-Aware Expert Regression (GAER) and Prototype-Guided Query Modulation (PGQM) to improve localization and objectness estimation for diverse visual elements, respectively. Extensive experiments show that ECADet consistently outperforms representative class-agnostic and proposal-based detectors on BTCO-Bench, demonstrating the effectiveness of expanded objectness discovery. Code and benchmark will be released.
