Please use this identifier to cite or link to this item:
Title: Learning discriminative hierarchical features for object recognition
Authors: Wang, Gang
Zuo, Zhen
Keywords: DRNTU::Engineering::Electrical and electronic engineering
Issue Date: 2014
Source: Zuo, Z, & Wang, G. (2014). Learning Discriminative Hierarchical Features for Object Recognition. IEEE Signal Processing Letters, 21(9), 1159 - 1163.
Series/Report no.: IEEE signal processing letters
Abstract: 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.
DOI: 10.1109/LSP.2014.2298888
Rights: © 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: [].
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:EEE Journal Articles

Files in This Item:
File Description SizeFormat 
Learning Discriminative Hierarchical Features for Object Recognition.pdf272 kBAdobe PDFThumbnail

Google ScholarTM



Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.