Learning Filter Basis for Convolutional Neural Network Compression
This addresses the parameter burden in CNNs for computer vision tasks, offering a compression method that is incremental in improving efficiency.
The paper tackles the problem of reducing the large number of parameters in convolutional neural networks (CNNs) by learning a basis for filters in convolutional layers, which approximates original filters to compress models while preserving accuracy, as validated on image classification and super-resolution benchmarks with favorable comparisons to state-of-the-art methods.
Convolutional neural networks (CNNs) based solutions have achieved state-of-the-art performances for many computer vision tasks, including classification and super-resolution of images. Usually the success of these methods comes with a cost of millions of parameters due to stacking deep convolutional layers. Moreover, quite a large number of filters are also used for a single convolutional layer, which exaggerates the parameter burden of current methods. Thus, in this paper, we try to reduce the number of parameters of CNNs by learning a basis of the filters in convolutional layers. For the forward pass, the learned basis is used to approximate the original filters and then used as parameters for the convolutional layers. We validate our proposed solution for multiple CNN architectures on image classification and image super-resolution benchmarks and compare favorably to the existing state-of-the-art in terms of reduction of parameters and preservation of accuracy.