发表机构
University of Palermo; ICAR National Research Council of Italy（巴勒莫大学; 意大利国家研究委员会ICAR研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出B-FOR框架，通过无背景监督学习类别无关检测的目标性，在三类数据集上较基线提升超10个AR点，泛化性优异。
AI 中文摘要
目标检测器通常在闭集监督下训练，未标注区域被隐含视为背景。在标注不完整时，该假设会引入目标性偏差：视觉上有效但未标注的物体被用作负样本，使目标性与标注分类法绑定，而非通用物体结构。此局限对类别无关检测和开放世界检测尤为突出。本文提出无背景目标性学习（B-FOR），这是一种密集类别无关检测框架，无需对未标注区域进行显式背景监督即可学习目标性。B-FOR将检测表述为预测密集多尺度物体中心与尺度场，目标假设由此作为局部空间结构出现。监督通过空间结构化软目标被限制在可靠标注区域，避免前景-背景区分。为支持从涌现的局部最大值解码，本文进一步引入位移感知尺度场，将物体范围建模为所学目标性场的空间变化属性。在PASCAL VOC、MS-COCO和Open Images上的实验表明，其对未见类别和跨数据集物体分布具有强泛化性。B-FOR较现有类别无关基线提升了超过10个平均召回率（AR）点。消融研究显示，局部目标性监督和位移感知尺度场对标注不完整时的类别无关定位均至关重要。代码可获取于：this https URL。
英文摘要
Object detectors are typically trained under closed-set supervision, where unlabeled regions are implicitly treated as background. Under incomplete annotations, this assumption introduces objectness bias: visually valid but unlabeled objects are used as negatives, tying objectness to the annotated taxonomy rather than generic object structure. This limitation is particularly problematic for class-agnostic and open-world detection. This paper proposes Background-Free Objectness Learning (B-FOR), a dense class-agnostic detection framework that learns objectness without explicit background supervision on unlabeled regions. B-FOR formulates detection as the prediction of dense multi-scale object-center and scale fields, from which object hypotheses emerge as local spatial structures. Supervision is confined to reliable annotated regions through spatially structured soft targets, avoiding foreground-background discrimination. To support decoding from emergent local maxima, the paper further introduces displacement-aware scale fields that model object extent as a spatially varying property of the learned objectness field. Experiments on PASCAL VOC, MS-COCO, and Open Images demonstrate strong generalization to unseen categories and cross-dataset object distributions. B-FOR improves recall by more than +10 AR points over prior class-agnostic baselines. Ablation studies show that both localized objectness supervision and displacement-aware scale fields are critical for class-agnostic localization under incomplete annotations. Code available at: https://github.com/Daniaawan/B-FOR.
CommentsAccepted at the British Machine Vision Conference (BMVC) 2026. This arXiv version includes supplementary material
Journal refBMVC 2026
