Abstract: In this paper, we propose hierarchical attention dual network for fine-grained image classification. The dual network can randomly select pairs of inputs from dataset and compare the differences between them through hierarchical attention features learning, which are used simultaneously to remove noise and retain salient features. In the loss function, it considers the losses of difference in paired images according to the intra-variance and inter-variance. In addition, we also collect the disaster scene dataset from remote sensing images and apply the proposed method to disaster scene classification, which contain complex scenes and multiple types of disasters. Compared to other methods, experimental results show that the dual network with hierarchical attention is robust to different datasets and performs better.

Key words: Dual network, Fine-grained image classification, Hierarchical attention features