# Zero-Shot Knowledge Distillation in Deep Networks

Source: [Zero-Shot Knowledge Distillation in Deep Networks](<https://www.sota2.com/research/paper/68fa65c61e209131cea0c6fd>)

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

Data updated: 2025-10-25T21:35:37.665Z

Authors: Gaurav Kumar Nayak, Konda Reddy Mopuri, Vaisakh Shaj, R. Venkatesh Babu, Anirban Chakraborty

Published: 2019-05-20T13:49:28.000Z

## Abstract

Knowledge distillation deals with the problem of training a smaller model (Student) from a high capacity source model (Teacher) so as to retain most of its performance. Existing approaches use either the training data or meta-data extracted from it in order to train the Student. However, accessing the dataset on which the Teacher has been trained may not always be feasible if the dataset is very large or it poses privacy or safety concerns (e.g., bio-metric or medical data). Hence, in this paper, we propose a novel data-free method to train the Student from the Teacher. Without even using any meta-data, we synthesize the Data Impressions from the complex Teacher model and utilize these as surrogates for the original training data samples to transfer its learning to Student via knowledge distillation. We, therefore, dub our method "Zero-Shot Knowledge Distillation" and demonstrate that our framework results in competitive generalization performance as achieved by distillation using the actual training data samples on multiple benchmark datasets.

## 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.

- [Model Stealing on CIFAR-10 (test)](<https://www.sota2.com/research/sota/model-stealing-on-cifar-10-test.md>): Model Stealing; CIFAR-10 (test); Synthetic Accuracy (Data-Free): 69.5.

- [Image Classification on CIFAR10 (Acc %)](<https://www.sota2.com/research/sota/image-classification-on-cifar10-acc-percent.md>): Image Classification; CIFAR10; Accuracy (%): 69.56.

- [Image Classification Top-1 Accuracy on CIFAR100 (test)](<https://www.sota2.com/research/sota/image-classification-top-1-accuracy-on-cifar100-test.md>): Image Classification; CIFAR100 (test); Top-1 Accuracy: 67.74.

- [Image Classification on CIFAR10 (test) (Accuracy)](<https://www.sota2.com/research/sota/image-classification-on-cifar10-test-accuracy.md>): Image Classification; CIFAR10 (test); Accuracy: 93.32.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1905.08114>)

[PDF](<https://arxiv.org/pdf/1905.08114.pdf>)
