Channel Pruning for Deep Neural Networks Via a Relaxed Groupwise Splitting Method

A relaxed groupwise splitting method (RGSM) is developed and evaluated for channel pruning of deep neural networks. Experiments with VGG-16 and ResNet-18 architectures on CIFAR-10/100 image data show that RGSM can achieve much higher channel sparsity than group Lasso method, while keeping comparable accuracy.