Knowledge distillation for optimization of quantized deep neural networks

Abstract

Knowledge distillation (KD) is a very popular method for model size reduction. Recently, the technique is exploited for quantized deep neural networks (QDNNs) training as a way to restore the performance sacrificed by word-length reduction. KD, however, employs additional hyper-parameters, such as temperature, coefficient, and the size of teacher network for QDNN training. We analyze the effect of these hyper-parameters for QDNN optimization with KD. We find that these hyper-parameters are inter-related, and also introduce a simple and effective technique that reduces \textit{coefficient} during training. With KD employing the proposed hyper-parameters, we achieve the test accuracy of 92.7% and 67.0% on Resnet20 with 2-bit ternary weights for CIFAR-10 and CIFAR-100 data sets, respectively.

References in corpus (9)

• Distilling the Knowledge in a Neural Network
• FitNets: Hints for Thin Deep Nets
• Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
• Deep Learning with Limited Numerical Precision
• Deep Learning with Low Precision by Half-wave Gaussian Quantization
• Effective Quantization Methods for Recurrent Neural Networks
• Recurrent Neural Networks With Limited Numerical Precision
• Low Precision RNNs: Quantizing RNNs Without Losing Accuracy
• Knowledge distillation using unlabeled mismatched images

Cited by in corpus (1)

• SQWA: Stochastic Quantized Weight Averaging for Improving the Generalization Capability of Low-Precision Deep Neural Networks