# Fully Convolutional Attention Networks for Fine-Grained Recognition

arXiv: https://arxiv.org/abs/1603.06765 · HTML: https://mlsanity.com/paper/1603.06765/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Mar 2016.

## Built on by (most cited first, 8 of 8)

- [Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes](https://mlsanity.com/paper/2111.15000/) (2021)
- [Differentiable Patch Selection for Image Recognition](https://mlsanity.com/paper/2104.03059/) (2021)
- [Fine-Grained Object Classification via Self-Supervised Pose Alignment](https://mlsanity.com/paper/2203.15987/) (2022)
- [DP-Net: Learning Discriminative Parts for image recognition](https://mlsanity.com/paper/2404.15037/) (2024)
- [Toward American Sign Language Processing in the Real World: Data, Tasks, and Methods](https://mlsanity.com/paper/2308.12419/) (2023)
- [COMIX: Compositional Explanations using Prototypes](https://mlsanity.com/paper/2501.06059/) (2025)
- [Learning a Discriminant Latent Space with Neural Discriminant Analysis](https://mlsanity.com/paper/2107.06209/) (2021)
- [Enhancing Fine-grained Image Classification through Attentive Batch Training](https://mlsanity.com/paper/2412.19606/) (2024)

## Abstract (arXiv)

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.