Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-Grained Image Recognition

Heliang Zheng, Jianlong Fu, Zheng-Jun Zha, Jiebo Luo; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 5012-5021

Abstract


Learning subtle yet discriminative features (e.g., beak and eyes for a bird) plays a significant role in fine-grained image recognition. Existing attention-based approaches localize and amplify significant parts to learn fine-grained details, which often suffer from a limited number of parts and heavy computational cost. In this paper, we propose to learn such fine-grained features from hundreds of part proposals by Trilinear Attention Sampling Network (TASN) in an efficient teacher-student manner. Specifically, TASN consists of 1) a trilinear attention module, which generates attention maps by modeling the inter-channel relationships, 2) an attention-based sampler which highlights attended parts with high resolution, and 3) a feature distiller, which distills part features into an object-level feature by weight sharing and feature preserving strategies. Extensive experiments verify that TASN yields the best performance under the same settings with the most competitive approaches, in iNaturalist-2017, CUB-Bird, and Stanford-Cars datasets.

Related Material


[pdf]
[bibtex]
@InProceedings{Zheng_2019_CVPR,
author = {Zheng, Heliang and Fu, Jianlong and Zha, Zheng-Jun and Luo, Jiebo},
title = {Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-Grained Image Recognition},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}