An improved object detection algorithm based on YOLO*

Abstract

Abstract Accuracy and speed have always been a measure of the performance of object detection algorithms. The current algorithms have reduced the detection speed on the basis of increasing a certain accuracy due to their complex structure. In response to this problem, this paper uses the RepVGG network to improve the original YOLOv3 structure, which uses a diversified branch structure to enhance the network feature extraction ability during training and transforms the training model into an equivalent VGG-like topology network model during inference. In addition, we use ASFF to deal with the problem of mutually restricted scales. Experiments show that compared with the original algorithm, the improved algorithm increases mAP by 0.51 on the VOC data set, and at the same time the speed increases by 10%.