Fine-grained Image Classification Based on Multi-scale Discrimination Module
In order to improve the performance of hybrid architecture in the field of fine-grained image classification,a Discriminant Module(DM)is proposed,which consists of two parts:Discriminant Feature Selection(DFS)and Multi-scale Feature Aggregation(MFA).By selecting the representative features of Top-K bird species in different attentional heads in Vision Transformer(ViT),the DFS module pays attention to the characteristics of different regions,promotes the synergistic effect of different discriminating regions,and reduces the feature redundancy.The MFA module aggregates discriminant characteristics information of birds at different scales.The experimental proof is carried out on an open source bird fine-grained dataset and compared with existing methods.The experimental results show that the proposed module has achieved some improvement in bird fine-grained image recognition.
国家科技期刊平台
NSTL
万方数据
