Acceleration of Deep Convolutional Neural Networks Using Adaptive Filter Pruning

摘要

While convolutional neural networks (CNNs) have achieved remarkable performance on various supervised and unsupervised learning tasks, they typically consist of a massive number of parameters. This results in significant memory requirements as well as a computational burden. Consequently, there is a growing need for filter-level pruning approaches for compressing CNN based models that not only reduce the total number of parameters but reduce the overall computation as well. We present a new min-max framework for the filter-level pruning of CNNs. Our framework jointly prunes and fine-tunes CNN model parameters, with an adaptive pruning rate, while maintaining the model’s predictive performance. Our framework consists of two modules: (1) An adaptive filter pruning (AFP) module, which minimizes the number of filters in the model; and (2) A pruning rate controller (PRC) module, which maximizes the accuracy during pruning. In addition, we also introduce orthogonality regularization in training of CNNs to reduce redundancy across filters of a particular layer. In the proposed approach, we prune the least important filters and, at the same time, reduce the redundancy level in the model by using orthogonality constraints during training. Moreover, unlike most previous approaches, our approach allows directly specifying the desired error tolerance instead of the pruning level. We perform extensive experiments for object classification (LeNet, VGG, MobileNet, and ResNet) and object detection (SSD, and Faster-RCNN) over benchmarked datasets such as MNIST, CIFAR, GTSDB, ImageNet, and MS-COCO. We also present several ablation studies to validate the proposed approach. Our compressed models can be deployed at run-time, without requiring any special libraries or hardware. Our approach reduces the number of parameters of VGG-16 by an impressive factor of 17.5X, and the number of FLOPS by 6.43X, with no loss of accuracy, significantly outperforming other state-of-the-art filter pruning methods.