Gaussian Guided IoU: A Better Metric for Balanced Learning on Object Detection

TL;DR

This paper introduces Gaussian Guided IoU (GGIoU), a new metric that emphasizes the proximity of anchor centers to object centers, improving training for slender objects and localization accuracy in object detection.

Contribution

The paper proposes GGIoU and a balanced learning method that assign multiple anchors to slender objects and enhance feature-object alignment during training.

Findings

Significant improvement in localization accuracy on PASCAL VOC and MS COCO.

Better handling of slender objects with multiple anchor assignments.

Enhanced feature-object alignment leads to improved detection performance.

Abstract

For most of the anchor-based detectors, Intersection over Union(IoU) is widely utilized to assign targets for the anchors during training. However, IoU pays insufficient attention to the closeness of the anchor's center to the truth box's center. This results in two problems: (1) only one anchor is assigned to most of the slender objects which leads to insufficient supervision information for the slender objects during training and the performance on the slender objects is hurt; (2) IoU can not accurately represent the alignment degree between the receptive field of the feature at the anchor's center and the object. Thus during training, some features whose receptive field aligns better with objects are missing while some features whose receptive field aligns worse with objects are adopted. This hurts the localization accuracy of models. To solve these problems, we firstly design Gaussian Guided IoU(GGIoU) which focuses more attention on the closeness of the anchor's center to the truth box's center. Then we propose GGIoU-balanced learning method including GGIoU-guided assignment strategy and GGIoU-balanced localization loss. The method can assign multiple anchors for each slender object and bias the training process to the features well-aligned with objects. Extensive experiments on the popular benchmarks such as PASCAL VOC and MS COCO demonstrate GGIoU-balanced learning can solve the above problems and substantially improve the performance of the object detection model, especially in the localization accuracy.