The Application of Two-Level Attention Models in Deep Convolutional Neural Network for Fine-Grained Image Classification

Tianjun Xiao, Yichong Xu, Kuiyuan Yang, Jiaxing Zhang, Yuxin Peng, Zheng Zhang; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 842-850

Abstract


Fine-grained classification is challenging because categories can only be discriminated by subtle and local differences. Variances in the pose, scale or rotation usually make the problem more difficult. Most fine-grained classification systems follow the pipeline of finding foreground object or object parts (where) to extract discriminative features (what). In this paper, we propose to apply visual attention to fine-grained classification task using deep neural network. Our pipeline integrates three types of attention: the bottom-up attention that propose candidate patches, the object-level top-down attention that selects relevant patches to a certain object, and the part-level top-down attention that localizes discriminative parts. We combine these attentions to train domain-specific deep nets, then use it to improve both the what and where aspects. Importantly, we avoid using expensive annotations like bounding box or part information from end-to-end. The weak supervision constraint makes our work easier to generalize. We have verified the effectiveness of the method on the subsets of ILSVRC2012 dataset and CUB200_2011 dataset. Our pipeline delivered significant improvements and achieved the best accuracy under the weakest supervision condition. The performance is competitive against other methods that rely on additional annotations.

Related Material


[pdf]
[bibtex]
@InProceedings{Xiao_2015_CVPR,
author = {Xiao, Tianjun and Xu, Yichong and Yang, Kuiyuan and Zhang, Jiaxing and Peng, Yuxin and Zhang, Zheng},
title = {The Application of Two-Level Attention Models in Deep Convolutional Neural Network for Fine-Grained Image Classification},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2015}
}