Extreme Network Compression via Filter Group Approximation
This addresses the need for efficient deployment of CNNs in resource-constrained environments, though it is incremental as it builds on existing compression techniques.
The paper tackles the problem of compressing deep convolutional neural networks by proposing a filter group approximation method, achieving over 80% reduction in FLOPs with less accuracy drop than state-of-the-art methods on models like VGG and ResNet.
In this paper we propose a novel decomposition method based on filter group approximation, which can significantly reduce the redundancy of deep convolutional neural networks (CNNs) while maintaining the majority of feature representation. Unlike other low-rank decomposition algorithms which operate on spatial or channel dimension of filters, our proposed method mainly focuses on exploiting the filter group structure for each layer. For several commonly used CNN models, including VGG and ResNet, our method can reduce over 80% floating-point operations (FLOPs) with less accuracy drop than state-of-the-art methods on various image classification datasets. Besides, experiments demonstrate that our method is conducive to alleviating degeneracy of the compressed network, which hurts the convergence and performance of the network.