Center Point Target Detection Algorithm Based on Improved Swin Transformer
Aiming at the shortcomings of Swin Transformer in extracting local feature information and expressing features,this paper proposes a center point target detection algorithm based on improved Swin Transformer to improve its performance in tar-get detection.By adjusting the network structure and introducing a deconvolution module to enhance the network's ability to ex-tract local feature information,using an adaptive two-dimensional Gaussian kernel and a regression head module to detect the cen-ter point of the target,so as to enhance the feature expression ability,and adding a dropout activation function to the Swin Trans-former block module to alleviate the network overfitting problem.The improved algorithm is validated on the Pascal VOC and MS COCO 2017 datasets,respectively.The experimental results show that the improved Swin Transformer algorithm achieves an ac-curacy of 81.1％on the Pascal VOC dataset and 37.2％on the MS COCO dataset,significantly superior to other mainstream ob-ject detection algorithms.
Deep learningImage processingObject detectionDeconvSwin Transformer
NETL
NSTL
万方数据
