arXiv Analytics

Sign in

arXiv:1903.06150 [cs.CV]AbstractReferencesReviewsResources

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

Published 2019-03-14Version 1

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.

Related articles: Most relevant | Search more
arXiv:1605.06878 [cs.CV] (Published 2016-05-23)
Mask-CNN: Localizing Parts and Selecting Descriptors for Fine-Grained Image Recognition
arXiv:1711.04047 [cs.CV] (Published 2017-11-11)
DeepKSPD: Learning Kernel-matrix-based SPD Representation for Fine-grained Image Recognition
arXiv:1806.05372 [cs.CV] (Published 2018-06-14)
Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition