Learning discriminative hierarchical features for object recognition

Hierarchical feature learning methods have demonstrated substantial improvements over the conventional hand-designed local features. However, recent approaches mainly perform feature learning in an unsupervised manner, where subtle differences between different classes can hardly be captured. In thi...

Full description

Saved in:
Bibliographic Details
Main Authors: Wang, Gang, Zuo, Zhen
Other Authors: School of Electrical and Electronic Engineering
Format: Article
Language:English
Published: 2014
Subjects:
Online Access:https://hdl.handle.net/10356/104852
http://hdl.handle.net/10220/20346
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-104852
record_format dspace
spelling sg-ntu-dr.10356-1048522020-03-07T14:00:36Z Learning discriminative hierarchical features for object recognition Wang, Gang Zuo, Zhen School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering Hierarchical feature learning methods have demonstrated substantial improvements over the conventional hand-designed local features. However, recent approaches mainly perform feature learning in an unsupervised manner, where subtle differences between different classes can hardly be captured. In this letter, we propose a discriminative hierarchical feature learning method, which learns a non-linear transformation to encode discriminative information in the feature space. We apply our features on two general image classification benchmarks: Caltech 101, STL-10, and a new fine-grained image classification dataset: NTU Tree-51. The results show that by employing discriminative constraint, our method consistently improves the performance with 3% to 7% in classification accuracy. Accepted version 2014-08-19T08:50:20Z 2019-12-06T21:41:14Z 2014-08-19T08:50:20Z 2019-12-06T21:41:14Z 2014 2014 Journal Article Zuo, Z, & Wang, G. (2014). Learning Discriminative Hierarchical Features for Object Recognition. IEEE Signal Processing Letters, 21(9), 1159 - 1163. https://hdl.handle.net/10356/104852 http://hdl.handle.net/10220/20346 10.1109/LSP.2014.2298888 en IEEE signal processing letters © 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: [http://dx.doi.org/10.1109/LSP.2014.2298888]. 4 p. application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic DRNTU::Engineering::Electrical and electronic engineering
spellingShingle DRNTU::Engineering::Electrical and electronic engineering
Wang, Gang
Zuo, Zhen
Learning discriminative hierarchical features for object recognition
description Hierarchical feature learning methods have demonstrated substantial improvements over the conventional hand-designed local features. However, recent approaches mainly perform feature learning in an unsupervised manner, where subtle differences between different classes can hardly be captured. In this letter, we propose a discriminative hierarchical feature learning method, which learns a non-linear transformation to encode discriminative information in the feature space. We apply our features on two general image classification benchmarks: Caltech 101, STL-10, and a new fine-grained image classification dataset: NTU Tree-51. The results show that by employing discriminative constraint, our method consistently improves the performance with 3% to 7% in classification accuracy.
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Wang, Gang
Zuo, Zhen
format Article
author Wang, Gang
Zuo, Zhen
author_sort Wang, Gang
title Learning discriminative hierarchical features for object recognition
title_short Learning discriminative hierarchical features for object recognition
title_full Learning discriminative hierarchical features for object recognition
title_fullStr Learning discriminative hierarchical features for object recognition
title_full_unstemmed Learning discriminative hierarchical features for object recognition
title_sort learning discriminative hierarchical features for object recognition
publishDate 2014
url https://hdl.handle.net/10356/104852
http://hdl.handle.net/10220/20346
_version_ 1681039077253578752