A multi-branch fine-grained recognition method based on dynamic localization and feature fusion
To solve the classification difficulties of small inter-class differences and large intra-class differences in fine-grained classification,an improved end-to-end fine-grained classification model(TB-former)is proposed based on Swin Transformer.In view of the interference of complex background on network recognition,the dynamic location module(DLModule)combining ECA,Resnet50 and SCDA is used to capture key objects,and a three-branch feature extraction module based on DLModule is de-signed to improve the ability of target discriminant feature extraction.In order to fully tap the rich fine-grained information contained in the three-branch features,a feature fusion method based on ECA is proposed to enhance the comprehensiveness and accuracy of the features,and improve the robustness of the network for fine-grained classification.The experimental results show that compared with the basic method,the accuracy of TBformer is improved by 3.19%in CUB-200-2011,3.47%in Stanford Dogs and 1.09%in NABirds.
fine grained recognitionfeature fusionattention mechanismmultiple branches
万方数据
维普
