Fully Convolutional Attention Networks for Fine-Grained Recognition

TL;DR

This paper introduces Fully Convolutional Attention Networks (FCANs), a reinforcement learning-based framework that localizes discriminative regions for fine-grained recognition without requiring detailed part annotations, improving efficiency and accuracy.

Contribution

The work proposes a weakly-supervised, fully-convolutional attention model for fine-grained recognition that is faster and more effective than previous methods.

Findings

Achieves state-of-the-art results on four fine-grained datasets.

Requires no expensive part annotations for training.

Speeds up training and testing through fully-convolutional architecture.

Abstract

Fine-grained recognition is challenging due to its subtle local inter-class differences versus large intra-class variations such as poses. A key to address this problem is to localize discriminative parts to extract pose-invariant features. However, ground-truth part annotations can be expensive to acquire. Moreover, it is hard to define parts for many fine-grained classes. This work introduces Fully Convolutional Attention Networks (FCANs), a reinforcement learning framework to optimally glimpse local discriminative regions adaptive to different fine-grained domains. Compared to previous methods, our approach enjoys three advantages: 1) the weakly-supervised reinforcement learning procedure requires no expensive part annotations; 2) the fully-convolutional architecture speeds up both training and testing; 3) the greedy reward strategy accelerates the convergence of the learning. We demonstrate the effectiveness of our method with extensive experiments on four challenging fine-grained benchmark datasets, including CUB-200-2011, Stanford Dogs, Stanford Cars and Food-101.