Attention for Fine-Grained Categorization

12/22/2014
by   Pierre Sermanet, et al.
0

This paper presents experiments extending the work of Ba et al. (2014) on recurrent neural models for attention into less constrained visual environments, specifically fine-grained categorization on the Stanford Dogs data set. In this work we use an RNN of the same structure but substitute a more powerful visual network and perform large-scale pre-training of the visual network outside of the attention RNN. Most work in attention models to date focuses on tasks with toy or more constrained visual environments, whereas we present results for fine-grained categorization better than the state-of-the-art GoogLeNet classification model. We show that our model learns to direct high resolution attention to the most discriminative regions without any spatial supervision such as bounding boxes, and it is able to discriminate fine-grained dog breeds moderately well even when given only an initial low-resolution context image and narrow, inexpensive glimpses at faces and fur patterns. This and similar attention models have the major advantage of being trained end-to-end, as opposed to other current detection and recognition pipelines with hand-engineered components where information is lost. While our model is state-of-the-art, further work is needed to fully leverage the sequential input.

READ FULL TEXT

page 2

page 4

page 7

page 11

research
03/20/2020

Three-branch and Mutil-scale learning for Fine-grained Image Recognition (TBMSL-Net)

ImageNet Large Scale Visual Recognition Challenge (ILSVRC) is one of the...
research
05/01/2021

Enhancing Fine-Grained Classification for Low Resolution Images

Low resolution fine-grained classification has widespread applicability ...
research
07/15/2014

Part-based R-CNNs for Fine-grained Category Detection

Semantic part localization can facilitate fine-grained categorization by...
research
09/25/2019

Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization

Fine-grained visual categorization (FGVC) is an important but challengin...
research
09/16/2021

Mask-Guided Feature Extraction and Augmentation for Ultra-Fine-Grained Visual Categorization

While the fine-grained visual categorization (FGVC) problems have been g...
research
06/23/2020

Facing the Hard Problems in FGVC

In fine-grained visual categorization (FGVC), there is a near-singular f...
research
03/04/2022

HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging

The rapid development of deep learning provides a better solution for th...

Please sign up or login with your details

Forgot password? Click here to reset