DAIS: Automatic Channel Pruning via Differentiable Annealing Indicator Search

Abstract

The convolutional neural network has achieved great success in fulfilling computer vision tasks despite large computation overhead against efficient deployment. Structured (channel) pruning is usually applied to reduce the model redundancy while preserving the network structure, such that the pruned network can be easily deployed in practice. However, existing structured pruning methods require hand-crafted rules which may lead to tremendous pruning space. In this paper, we introduce Differentiable Annealing Indicator Search (DAIS) that leverages the strength of neural architecture search in the channel pruning and automatically searches for the effective pruned model with given constraints on computation overhead. Specifically, DAIS relaxes the binarized channel indicators to be continuous and then jointly learns both indicators and model parameters via bi-level optimization. To bridge the non-negligible discrepancy between the continuous model and the target binarized model, DAIS proposes an annealing-based procedure to steer the indicator convergence towards binarized states. Moreover, DAIS designs various regularizations based on a priori structural knowledge to control the pruning sparsity and to improve model performance. Experimental results show that DAIS outperforms state-of-the-art pruning methods on CIFAR-10, CIFAR-100, and ImageNet.

Accepted to IEEE TNNLS

References in corpus (7)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Neural Architecture Search with Reinforcement Learning
• Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
• To prune, or not to prune: exploring the efficacy of pruning for model compression
• Learning Structured Sparsity in Deep Neural Networks
• Channel Pruning for Accelerating Very Deep Neural Networks
• Towards Optimal Structured CNN Pruning via Generative Adversarial Learning

Cited by in corpus (5)

• Structured Pruning for Deep Convolutional Neural Networks: A survey
• CATRO: Channel Pruning via Class-Aware Trace Ratio Optimization
• DASS: Differentiable Architecture Search for Sparse neural networks
• Exploring Gradient Flow Based Saliency for DNN Model Compression
• Layer Pruning with Consensus: A Triple-Win Solution