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 a global one 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.

本文介绍了Trilinear Attention Sampling Network (TASN)，一种高效的fine-grained feature学习方法，通过从数百个部件提议中学习特征并使用多层次的注意力机制来改善细粒度识别性能。在iNaturalist-2017，CUB-Bird和Stanford-Cars数据集上的实验表明，TASN在相同配置下的性能优于其他竞争方法。

寻找细节中的恶魔：学习三线性注意力采样网络进行细粒度图像识别