Selective feature block and joint IoU loss for object detection

Abstract

Object detection is an important problem in the field of computer vision, and feature fusion and bounding box regression are indispensable in mainstream object detection approaches. However, some detectors adopt Feature Pyramid Network, which increases training and detection time. In terms of the regression loss function, some recent techniques based on Intersection over Union (IoU) loss have negative effects on bounding box regression. To overcome these shortcomings, we propose Selective Feature Block (SFBlock) and Joint IoU (JIoU) loss in this article. The proposed SFBlock adaptively selects the features extracted from the Backbone and fuses them into a new feature. We add a penalty term of the intersection area between the prediction box and the target box on Generalized IoU (GIoU) loss to solve the problem that GIoU loss degenerates into IoU loss when the prediction box and the target box are surrounded by each other. A large number of ablation experiments and comparative experiments are carried out to prove the effectiveness of the proposed methods on various models and datasets.