Abstract: In order to address the challenges of high intra-class variances and low inter-class variances in fine-grained image classification,a multi-branch attention-augmented convolution neural network is proposed to solve the problem.The pre-trained Inception-V3 network is used to extract basic feature.In order to solve the problem that features are extracted from one part of an object and encourage the network to pay more attention to the discriminative features of different parts,we apply self-constrained attention-wised cropping and self-constrained attention-wised erasing on the central parts of the original images.It also improves the detection accuracy of object locations.Meanwhile,a central regularization loss function is proposed to constrain attention-augmented training process to obtain better attention regions and expand the gap between different classes of images.Comprehensive experiments on three benchmark datasets show that our approach surpasses the state-of-art works.

Key words: Fine-grained image classification, Weakly supervised learning, Multi-branch attention-augmentation, Convolutional neural network, Central regularization loss