Enhancing Data-Free Adversarial Distillation with Activation Regularization and Virtual Interpolation

TL;DR

This paper introduces activation regularization and virtual interpolation techniques to improve data-free adversarial knowledge distillation, significantly enhancing the efficiency and accuracy of student models without access to original training data.

Contribution

It proposes novel activation regularizer and virtual interpolation methods that boost data generation efficiency and model performance in data-free distillation.

Findings

Achieves 95.42% accuracy on CIFAR-10

Achieves 77.05% accuracy on CIFAR-100

Outperforms state-of-the-art data-free distillation methods

Abstract

Knowledge distillation refers to a technique of transferring the knowledge from a large learned model or an ensemble of learned models to a small model. This method relies on access to the original training set, which might not always be available. A possible solution is a data-free adversarial distillation framework, which deploys a generative network to transfer the teacher model's knowledge to the student model. However, the data generation efficiency is low in the data-free adversarial distillation. We add an activation regularizer and a virtual interpolation method to improve the data generation efficiency. The activation regularizer enables the students to match the teacher's predictions close to activation boundaries and decision boundaries. The virtual interpolation method can generate virtual samples and labels in-between decision boundaries. Our experiments show that our approach surpasses state-of-the-art data-free distillation methods. The student model can achieve 95.42% accuracy on CIFAR-10 and 77.05% accuracy on CIFAR-100 without any original training data. Our model's accuracy is 13.8% higher than the state-of-the-art data-free method on CIFAR-100.