Accelerating Convolutional Neural Networks with Dominant Convolutional Kernel and Knowledge Pre-regression

摘要

Aiming at accelerating the test time of deep convolutional neural networks (CNNs), we propose a model compression method that contains a novel dominant kernel (DK) and a new training method called knowledge pre-regression (KP). In the combined model DK~2PNet, DK is presented to significantly accomplish a low-rank decomposition of convolutional kernels, while KP is employed to transfer knowledge of intermediate hidden layers from a larger teacher network to its compressed student network on the basis of a cross entropy loss function instead of previous Euclidean distance. Compared to the latest results, the experimental results achieved on CIFAR-10, CIFAR-100, MNIST, and SVHN benchmarks show that our DK~2PNet method has the best performance in the light of being close to the state of the art accuracy and requiring dramatically fewer number of model parameters.