Learning discriminative hierarchical features for object recognition

• Main Authors: Wang, Gang, Zuo, Zhen
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2014
• Subjects: DRNTU::Engineering::Electrical and electronic engineering
• Online Access: https://hdl.handle.net/10356/104852; http://hdl.handle.net/10220/20346
• Institution: Nanyang Technological University

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.