Bilinear Residual Attention Networks for Fine-Grained Image Classification

Fine-grained images have a highly similar appearance, and the differences arc often reflected in local regions. Extracting discriminative local features plays a key role in fine-grained classification. Attention mechanism is a common strategy to solve the problems above. Therefore, we propose an improved bilinear residual attention network based on bilinear convolutional neural network model in this paper: the feature function of the original model is replaced by deep residual network with a stronger feature extraction capability, then channel attention module and spatial attention module arc added between the residual units respectively to obtain different dimensions and richer attention features. Ablation and contrast experiments were performed on three fine-grained image datasets CUB-200-2011, Stanford Dogs, and Stanford Cars, the classification accuracy of the improved model reached 87.2%, 89.2% and 92.5%, respectively. Experimental results show that our method can achieve better classification results than the original model and other mainstream fine-grained classification algorithms.