Journal
IEEE SIGNAL PROCESSING LETTERS
Volume 21, Issue 9, Pages 1159-1163Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LSP.2014.2298888
Keywords
Discriminant analysis; hierarchical feature learning; patch-to-class distance; object recognition
Categories
Funding
- Singapore National Research Foundation under its IDM Futures Funding Initiative
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available