Data-Free Knowledge Distillation for Deep Neural Networks
This addresses a practical limitation in model compression for scenarios where training data is inaccessible, such as in biometrics or large-scale datasets, though it appears incremental as it builds on existing knowledge distillation techniques.
The paper tackles the problem of compressing deep neural networks without access to the original training data, which is often unavailable due to privacy or size constraints, and presents a data-free knowledge distillation method that achieves compression while retaining accuracy using only extra metadata.
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.