Target Detection Algorithm Based on Improved Swin Transformer
In the task of target detection,Detection Transformer(DETR)-based anchorless frame methods have received widespread attention because they do not rely on complex post-processing steps such as non-maximal value suppression.Aiming at the shortcomings of ResNet(Residual Network),the residual backbone network used in DETR,in terms of its ability to extract global information,this paper proposes a target detection algorithm based on the improved Swin Trans-former.The backbone network of the model is improved based on Swin Transformer,where a new normalization method called"post-normalization"is used,which generates milder activa-tion values throughout the network,and then the backbone network is combined with the fea-ture pyramid to obtain feature representations at different scales,thus better adapt to target or image variations at different scales.
NETL
NSTL
万方数据
