Self-Adaptive Network Pruning
arXiv:1910.08906
Abstract
Deep convolutional neural networks have been proved successful on a wide range of tasks, yet they are still hindered by their large computation cost in many industrial scenarios. In this paper, we propose to reduce such cost for CNNs through a self-adaptive network pruning method (SANP). Our method introduces a general Saliency-and-Pruning Module (SPM) for each convolutional layer, which learns to predict saliency scores and applies pruning for each channel. Given a total computation budget, SANP adaptively determines the pruning strategy with respect to each layer and each sample, such that the average computation cost meets the budget. This design allows SANP to be more efficient in computation, as well as more robust to datasets and backbones. Extensive experiments on 2 datasets and 3 backbones show that SANP surpasses state-of-the-art methods in both classification accuracy and pruning rate.
10 pages, 5 figures, conference
References in corpus (5)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
- DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
- Neural GPUs Learn Algorithms
- Discrete Autoencoders for Sequence Models