Data-Free Knowledge Distillation for Deep Neural Networks
Abstract
Recent advances in model compression have provided procedures for compressing large neural networks to a fraction of their original size while retaining most if not all of their accuracy. However, all of these approaches rely on access to the original training set, which might not always be possible if the network to be compressed was trained on a very large dataset, or on a dataset whose release poses privacy or safety concerns as may be the case for biometrics tasks. We present a method for data-free knowledge distillation, which is able to compress deep neural networks trained on large-scale datasets to a fraction of their size leveraging only some extra metadata to be provided with a pretrained model release. We also explore different kinds of metadata that can be used with our method, and discuss tradeoffs involved in using each of them.
Cite
@article{arxiv.1710.07535,
title = {Data-Free Knowledge Distillation for Deep Neural Networks},
author = {Raphael Gontijo Lopes and Stefano Fenu and Thad Starner},
journal= {arXiv preprint arXiv:1710.07535},
year = {2017}
}
Comments
Accepted to NIPS 2017 Workshop on Learning with Limited Data. Under review at AISTATS 2018