跳跃式监视
计算机科学
最小边界框
回归
趋同(经济学)
交叉口(航空)
算法
功能(生物学)
数学优化
数学
人工智能
统计
图像(数学)
工程类
进化生物学
生物
航空航天工程
经济增长
经济
作者
Yifan Zhang,Wei Ren,Zhang Zhang,Zhen Jia,Liang Wang,Tieniu Tan
出处
期刊:Neurocomputing
[Elsevier]
日期:2022-09-01
卷期号:506: 146-157
被引量:416
标识
DOI:10.1016/j.neucom.2022.07.042
摘要
In object detection, bounding box regression (BBR) is a crucial step that determines the object localization performance. However, we find that most previous loss functions for BBR have two main drawbacks: (i) Both ℓn-norm and IOU-based loss functions are inefficient to depict the objective of BBR, which leads to slow convergence and inaccurate regression results. (ii) Most of the loss functions ignore the imbalance problem in BBR that the large number of anchor boxes which have small overlaps with the target boxes contribute most to the optimization of BBR. To mitigate the adverse effects caused thereby, we perform thorough studies to exploit the potential of BBR losses in this paper. Firstly, an Efficient Intersection over Union (EIOU) loss is proposed, which explicitly measures the discrepancies of three geometric factors in BBR, i.e., the overlap area, the central point and the side length. After that, we state the Effective Example Mining (EEM) problem and propose a regression version of focal loss to make the regression process focus on high-quality anchor boxes. Finally, the above two parts are combined to obtain a new loss function, namely Focal-EIOU loss. Extensive experiments on both synthetic and real datasets are performed. Notable superiorities on both the convergence speed and the localization accuracy can be achieved over other BBR losses.
科研通智能强力驱动
Strongly Powered by AbleSci AI