# Large-Scale Generative Data-Free Distillation

Source: [Large-Scale Generative Data-Free Distillation](<https://www.sota2.com/research/paper/68fa68dd1e209131cea1ec9e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:47:52.778Z

Authors: Liangchen Luo, Mark Sandler, Zi Lin, Andrey Zhmoginov, Andrew Howard

Published: 2020-12-10T10:54:38.000Z

## Abstract

Knowledge distillation is one of the most popular and effective techniques for knowledge transfer, model compression and semi-supervised learning. Most existing distillation approaches require the access to original or augmented training samples. But this can be problematic in practice due to privacy, proprietary and availability concerns. Recent work has put forward some methods to tackle this problem, but they are either highly time-consuming or unable to scale to large datasets. To this end, we propose a new method to train a generative image model by leveraging the intrinsic normalization layers' statistics of the trained teacher network. This enables us to build an ensemble of generators without training data that can efficiently produce substitute inputs for subsequent distillation. The proposed method pushes forward the data-free distillation performance on CIFAR-10 and CIFAR-100 to 95.02% and 77.02% respectively. Furthermore, we are able to scale it to ImageNet dataset, which to the best of our knowledge, has never been done using generative models in a data-free setting.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2012.05578>)

[PDF](<https://arxiv.org/pdf/2012.05578.pdf>)
