Published on Wed Jan 20 2021

Focal and Efficient IOU Loss for Accurate Bounding Box Regression

Yi-Fan Zhang, Weiqiang Ren, Zhang Zhang, Zhen Jia, Liang Wang, Tieniu Tan

In object detection, bounding box regression (BBR) is a crucial step that determines the object localization performance. Most previous loss functions for BBR have two main drawbacks. The large number of anchor boxes which have small overlaps with the target boxes contribute most to the optimization of BBR.

0
0
0
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 -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.

Tue Nov 19 2019
Computer Vision
Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression
Bounding box regression is the crucial step in object detection. We propose a Distance-IoU(DIoU) loss by incorporating the normalized distance between the predicted box and the target box. This loss converges much faster in training than IoU and GIoU losses.
0
0
0
Thu Apr 01 2021
Computer Vision
SCALoss: Side and Corner Aligned Loss for Bounding Box Regression
0
0
0
Tue Dec 01 2020
Computer Vision
Confluence: A Robust Non-IoU Alternative to Non-Maxima Suppression in Object Detection
Confluence is a novel non-Intersection over Union (IoU) alternative to NMS. It overcomes the inherent limitations of IoU-based NMS variants. Confluence is experimentally validated on the MS COCO and CrowdHuman benchmarks.
0
0
0
Mon Jul 30 2018
Computer Vision
Acquisition of Localization Confidence for Accurate Object Detection
IoU-Net learning to predict the IoU between each detected bounding box and the matched ground-truth. The network acquires this confidence of localization, which improves the NMS procedure by preserving accurately localized bounding boxes.
0
0
0
Sun Sep 23 2018
Computer Vision
Bounding Box Regression with Uncertainty for Accurate Object Detection
Large-scale object detection datasets (e.g., MS-COCO) try to define the ground truth bounding boxes as clear as possible. In this paper, we propose a novel bounding box regression loss for learning bounding box transformation and localization variance together. Our loss greatly.
0
0
0
Mon Jun 08 2020
Computer Vision
Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection
One-stage detector basically formulates object detection as dense boxes. The classification is usually optimized by Focal Loss. The box location is commonly learned under Dirac delta distribution. A recent trend for one-stage detectors is to introduce an individual prediction branch.
0
0
0