English

Sparse Deep Stacking Network for Image Classification

Computer Vision and Pattern Recognition 2015-01-06 v1 Machine Learning Neural and Evolutionary Computing

Abstract

Sparse coding can learn good robust representation to noise and model more higher-order representation for image classification. However, the inference algorithm is computationally expensive even though the supervised signals are used to learn compact and discriminative dictionaries in sparse coding techniques. Luckily, a simplified neural network module (SNNM) has been proposed to directly learn the discriminative dictionaries for avoiding the expensive inference. But the SNNM module ignores the sparse representations. Therefore, we propose a sparse SNNM module by adding the mixed-norm regularization (l1/l2 norm). The sparse SNNM modules are further stacked to build a sparse deep stacking network (S-DSN). In the experiments, we evaluate S-DSN with four databases, including Extended YaleB, AR, 15 scene and Caltech101. Experimental results show that our model outperforms related classification methods with only a linear classifier. It is worth noting that we reach 98.8% recognition accuracy on 15 scene.

Keywords

Cite

@article{arxiv.1501.00777,
  title  = {Sparse Deep Stacking Network for Image Classification},
  author = {Jun Li and Heyou Chang and Jian Yang},
  journal= {arXiv preprint arXiv:1501.00777},
  year   = {2015}
}

Comments

8 pages, 3 figures, AAAI-2015

R2 v1 2026-06-22T07:50:45.453Z