Please use this identifier to cite or link to this item:
|Title:||Learning discriminative hierarchical features for object recognition||Authors:||Wang, Gang
|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.||URI:||https://hdl.handle.net/10356/104852
|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: [http://dx.doi.org/10.1109/LSP.2014.2298888].||Fulltext Permission:||open||Fulltext Availability:||With Fulltext|
|Appears in Collections:||EEE Journal Articles|
Files in This Item:
|Learning Discriminative Hierarchical Features for Object Recognition.pdf||272 kB||Adobe PDF|
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.