DAF-NET: a saliency based weakly supervised method of dual attention fusion for fine-grained image classification

TL;DR

This paper introduces DAF-NET, a novel weakly supervised approach that fuses dual attention mechanisms to improve fine-grained image classification accuracy.

Contribution

It proposes a new method that combines activation and detection based attention for better feature discrimination in fine-grained classification.

Findings

Achieves 87.6% accuracy with student net alone on CUB dataset.

Improves to 89.1% accuracy when using teacher-student cooperation.

Demonstrates effectiveness of dual attention fusion in fine-grained tasks.

Abstract

Fine-grained image classification is a challenging problem, since the difficulty of finding discriminative features. To handle this circumstance, basically, there are two ways to go. One is use attention based method to focus on informative areas, while the other one aims to find high order between features. Further, for attention based method there are two directions, activation based and detection based, which are proved effective by scholars. However ,rare work focus on fusing two types of attention with high order feature. In this paper, we propose a novel DAF method which fuse two types of attention and use them to as PAF(part attention filter) in deep bilinear transformation module to mine the relationship between separate parts of an object. Briefly, our network constructed by a student net who attempt to output two attention maps and a teacher net uses these two maps as empirical information to refine the result. The experiment result shows that only student net could get 87.6% accuracy in CUB dataset while cooperating with teacher net could achieve 89.1% accuracy.