Attention-Based Multi-Task Learning For Fine-Grained Image Classification

Fine-Grained Image Classification is an inherently challenging task because of its inter-class similarity and intra-class variance. Most existing studies solve this problem by localization-and-classification strategies, which, however, always causes the problem of information loss or heavy computati...

Full description

Saved in:
Bibliographic Details
Main Authors: Liu, Dichao, Wang, Yu, Mase, Kenji, Kato, Jien
Format: Conference Proceeding
Language:English
Subjects:
Agriculture
Attention Learning
Automobiles
Conferences
Convolutional neural networks
Fine-grained Classification
Image processing
Multi-task Learning
Regulation
Task analysis
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Fine-Grained Image Classification is an inherently challenging task because of its inter-class similarity and intra-class variance. Most existing studies solve this problem by localization-and-classification strategies, which, however, always causes the problem of information loss or heavy computational expenses. Instead of localization-and-classification strategy, we propose a novel end-to-end optimization procedure named Multi-Task Attention Learning (MTAL), which reinforces the neural network' correspondence to attention regions. Experimental results on CUB-Birds and Stanford Cars show that our procedure distinctly outperforms the baselines and is comparable with state-of-the-art studies despite its simplicity*.
ISSN:2381-8549
DOI:10.1109/ICIP42928.2021.9506745