2021/08/31 by Zhouyang Xie, Yan Fu, Xie, Zhouyang +7
Computer Science · #Advanced Neural Network Applications #Adversarial Robustness in Machine Learning #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences
paper · pdf · doi:10.48550/arxiv.2108.13728
openalex publication_date 2021/08/31 · openalex created_date 2021/09/13 · openalex updated_date 2026/07/28
Channel pruning is a promising technique to compress the parameters of deep convolutional neural networks(DCNN) and to speed up the inference. This paper aims to address the long-standing inefficiency of channel pruning. Most channel pruning methods recover the prediction accuracy by re-training the pruned model from the remaining parameters or random initialization. This re-training process is heavily dependent on the sufficiency of computational resources, training data, and human interference(tuning the training strategy). In this paper, a highly efficient pruning method is proposed to significantly reduce the cost of pruning DCNN. The main contributions of our method include: 1) pruning compensation, a fast and data-efficient substitute of re-training to minimize the post-pruning reconstruction loss of features, 2) compensation-aware pruning(CaP), a novel pruning algorithm to remove redundant or less-weighted channels by minimizing the loss of information, and 3) binary structural search with step constraint to minimize human interference. On benchmarks including CIFAR-10/100 and ImageNet, our method shows competitive pruning performance among the state-of-the-art retraining-based pruning methods and, more importantly, reduces the processing time by 95% and data usage by 90%.