Sparse Deep Stacking Network for Image Classification
This work addresses computational bottlenecks in image classification for researchers, though it is incremental as it builds on existing simplified neural network modules.
The authors tackled the computational expense of sparse coding inference by proposing a sparse deep stacking network (S-DSN) that incorporates mixed-norm regularization into simplified neural network modules, achieving 98.8% recognition accuracy on the 15 scene database and outperforming related methods.
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.