Learning Discriminative Hierarchical Features for Object Recognition
Authors:
- 9 January 2014
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 21 (9) , 1159-1163
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.Keywords
Funding Information
- Singapore National Research Foundation under its IDM Futures Funding Initiative and administered by the Interactive and Digital Media Programme Office Media Development Authority
This publication has 11 references indexed in Scilit:
- Local Naive Bayes Nearest Neighbor for image classification2012
- Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis2011
- Learning image representations from the pixel level via hierarchical sparse coding2011
- Locality-constrained Linear Coding for image classification2010
- Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations2009
- In defense of Nearest-Neighbor based image classification2008
- Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categoriesComputer Vision and Image Understanding, 2007
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories2006
- Histograms of Oriented Gradients for Human Detection2005