Deep Model Compression: Distilling Knowledge from Noisy Teachers

TL;DR

This paper introduces a noise-regularized teacher-student framework for deep model compression that improves runtime and training efficiency, demonstrated through experiments on CIFAR-10, SVHN, and MNIST datasets.

Contribution

It extends the teacher-student framework by incorporating noise-based regularization to enhance student network performance and efficiency.

Findings

Improved student network performance with noise regularization.

Effective on multiple datasets including CIFAR-10, SVHN, and MNIST.

Promising empirical results demonstrating the approach's potential.

Abstract

The remarkable successes of deep learning models across various applications have resulted in the design of deeper networks that can solve complex problems. However, the increasing depth of such models also results in a higher storage and runtime complexity, which restricts the deployability of such very deep models on mobile and portable devices, which have limited storage and battery capacity. While many methods have been proposed for deep model compression in recent years, almost all of them have focused on reducing storage complexity. In this work, we extend the teacher-student framework for deep model compression, since it has the potential to address runtime and train time complexity too. We propose a simple methodology to include a noise-based regularizer while training the student from the teacher, which provides a healthy improvement in the performance of the student network. Our experiments on the CIFAR-10, SVHN and MNIST datasets show promising improvement, with the best performance on the CIFAR-10 dataset. We also conduct a comprehensive empirical evaluation of the proposed method under related settings on the CIFAR-10 dataset to show the promise of the proposed approach.