2021/01/20 by Yifan Zhang, Yi-Fan Zhang, Zhang, Yi-Fan +10 · 6 citations
Computer Science · Engineering · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Medical Imaging and Analysis #cs.CV
paper · pdf · doi:10.48550/arxiv.2101.08158
openalex publication_date 2021/01/20 · arxiv created 2022/07/16 · arxiv updated 2022/07/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.