Supervised Translation-Invariant Sparse Coding

12 years 10 months ago
Supervised Translation-Invariant Sparse Coding
In this paper, we propose a novel supervised hierarchical sparse coding model based on local image descriptors for classification tasks. The supervised dictionary training is performed via back-projection, by minimizing the training error of classifying the image level features, which are extracted by max pooling over the sparse codes within a spatial pyramid. Such a max pooling procedure across multiple spatial scales offer the model translation invariant properties, similar to the Convolutional Neural Network (CNN). Experiments show that our supervised dictionary improves the performance of the proposed model significantly over the unsupervised dictionary, leading to state-of-the-art performance on diverse image databases. Further more, our supervised model targets learning linear features, implying its great potential in handling large scale datasets in real applications.
Jianchao Yang, Kai Yu, Thomas Huang
Added 29 Mar 2010
Updated 14 May 2010
Type Conference
Year 2010
Where CVPR
Authors Jianchao Yang, Kai Yu, Thomas Huang
Comments (0)