Image Classification with A Deep Network Model based on Compressive Sensing
This work addresses parameter complexity in deep learning for image classification, but it appears incremental as it applies compressive sensing to a standard dataset.
The authors tackled the problem of simplifying deep network parameters by proposing CSNet, a cascaded compressive sensing model for image classification, and achieved higher classification accuracy on the MNIST dataset.
To simplify the parameter of the deep learning network, a cascaded compressive sensing model "CSNet" is implemented for image classification. Firstly, we use cascaded compressive sensing network to learn feature from the data. Secondly, CSNet generates the feature by binary hashing and block-wise histograms. Finally, a linear SVM classifier is used to classify these features. The experiments on the MNIST dataset indicate that higher classification accuracy can be obtained by this algorithm.