发表机构
Beijing University of Technology; ShanghaiTech University; Beijing Institute of Technology; Beijing Electronic Science and Technology Institute; Zhengzhou University; Yunnan Normal University（北京工业大学; 上海科技大学; 北京理工大学; 北京电子科技学院; 郑州大学; 云南师范大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究视觉检测任务中边界框优化问题，提出分数语义IoU损失，通过设计语义相似性度量构建SIoU损失，再扩展为分数阶形式的FrSIoU损失，积累历史IoU状态正则化梯度，提升不同任务性能。
AI 中文摘要
边界框是视觉检测任务中目标定位的基础。其中，有向边界框在视觉检测任务中被广泛使用，能提供更精确的方向表示。一般来说，基于交并比（IoU）的损失被广泛用于优化框回归。然而，基于IoU的框优化存在两个关键问题：仅依赖几何属性而忽略语义线索；方向优化存在不稳定梯度，导致方向收敛振荡。本文提出分数语义IoU损失，通过梯度稳定化实现统一的语义-几何学习。首先，设计语义相似性度量来指导IoU优化，构建带有自适应梯度门控机制的语义IoU损失（SIoU损失）。然后，重新审视有向框优化中的梯度不稳定问题，将SIoU损失扩展为分数阶形式以构建分数语义IoU损失（FrSIoU损失）。FrSIoU损失在边界框优化过程中积累历史IoU状态来正则化异常梯度。大量实验表明，该方法在不同边界框公式和各种视觉检测任务中都能实现稳定的性能提升。代码将在GitHub上提供。
英文摘要
Bounding boxes are fundamental for object localization in visual detection tasks. Among them, oriented bounding boxes are widely used in visual detection tasks, which provide a more precise directional representation. Generally, IoU-based losses are widely adopted to optimize box regression. However, we observed that IoU-driven box optimization suffers from two key issues: (1) it relies solely on geometric properties while ignoring semantic cues; (2) orientation optimization suffers from unstable gradients, causing oscillations in orientation convergence. In this paper, we propose a Fractional Semantic IoU loss to achieve unified semantic-geometric learning with gradient stabilization. First, we design a semantic similarity metric to guide IoU optimization, building a Semantic IoU loss (SIoU loss) with an adaptive gradient gating mechanism. Then, we revisit the gradient instability issue in oriented box optimization and extend the SIoU loss to a fractional-order formulation to build the \textbf{Fr}actional \textbf{S}emantic \textbf{IoU} \textbf{loss} (FrSIoU loss). The FrSIoU loss accumulates historical IoU states to regularize abnormal gradients during bounding box optimization process. Extensive experiments demonstrate that our approach achieves stable performance gains across different bounding box formulations and diverse visual detection tasks. The code will be available on GitHub.
