Focal and Efficient IOU Loss for Accurate Bounding Box Regression

TL;DR

This paper introduces Focal-EIOU loss, a novel bounding box regression loss that improves convergence speed and localization accuracy by explicitly modeling geometric discrepancies and addressing sample imbalance.

Contribution

The paper proposes the Focal-EIOU loss combining geometric discrepancy measurement with a regression focal loss to enhance BBR performance.

Findings

Focal-EIOU achieves faster convergence in training.

It improves localization accuracy over existing BBR losses.

The method performs well on synthetic and real datasets.

Abstract

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 $\ell_n$-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.