Fully Convolutional Attention Networks for Fine-Grained Recognition

03/22/2016
by   Xiao Liu, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 4

page 8

research
06/28/2016

Diversified Visual Attention Networks for Fine-Grained Object Classification

Fine-grained object classification is a challenging task due to the subt...
research
05/23/2016

Mask-CNN: Localizing Parts and Selecting Descriptors for Fine-Grained Image Recognition

Fine-grained image recognition is a challenging computer vision problem,...
research
06/16/2018

Part-Aware Fine-grained Object Categorization using Weakly Supervised Part Detection Network

Fine-grained object categorization aims for distinguishing objects of su...
research
11/16/2018

Learning Where to Fixate on Foveated Images

Foveation, the ability to sequentially acquire high-acuity regions of a ...
research
10/06/2021

Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection

In industrial manufacturing processes, errors frequently occur at unpred...
research
07/04/2020

End-to-end Learning of a Fisher Vector Encoding for Part Features in Fine-grained Recognition

Part-based approaches for fine-grained recognition do not show the expec...
research
09/02/2018

Learning to Navigate for Fine-grained Classification

Fine-grained classification is challenging due to the difficulty of find...

Please sign up or login with your details

Forgot password? Click here to reset