Sparse Deep Stacking Network for Image Classification


  • Jun Li Nanjing University of Science and Technology
  • Heyou Chang Nanjing University of Science and Technology
  • Jian Yang Nanjing University of Science and Technology



Deep learning, stacking networks, sparse representations, image classification


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.




How to Cite

Li, J., Chang, H., & Yang, J. (2015). Sparse Deep Stacking Network for Image Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 29(1).