Control Distance IoU and Control Distance IoU Loss Function for Better Bounding Box Regression

Abstract

Numerous improvements for feedback mechanisms have contributed to the great progress in object detection. In this paper, we first present an evaluation-feedback module, which is proposed to consist of evaluation system and feedback mechanism. Then we analyze and summarize the disadvantages and improvements of traditional evaluation-feedback module. Finally, we focus on both the evaluation system and the feedback mechanism, and propose Control Distance IoU and Control Distance IoU loss function (or CDIoU and CDIoU loss for short) without increasing parameters or FLOPs in models, which show different significant enhancements on several classical and emerging models. Some experiments and comparative tests show that coordinated evaluation-feedback module can effectively improve model performance. CDIoU and CDIoU loss have different excellent performances in several models such as Faster R-CNN, YOLOv4, RetinaNet and ATSS. There is a maximum AP improvement of 1.9% and an average AP of 0.8% improvement on MS COCO dataset, compared to traditional evaluation-feedback modules.

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• YOLOv4: Optimal Speed and Accuracy of Object Detection
• Rethinking Atrous Convolution for Semantic Image Segmentation
• DSSD : Deconvolutional Single Shot Detector
• Going Deeper with Convolutions
• Learning Deconvolution Network for Semantic Segmentation
• Augmentation for small object detection
• Corner Proposal Network for Anchor-free, Two-stage Object Detection