# DeGAN : Data-Enriching GAN for Retrieving Representative Samples from a Trained Classifier

Source: [DeGAN : Data-Enriching GAN for Retrieving Representative Samples from a Trained Classifier](<https://www.sota2.com/research/paper/68fa66d11e209131cea1295d>)

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

Data updated: 2025-10-28T13:56:41.311Z

Authors: Sravanti Addepalli, Gaurav Kumar Nayak, Anirban Chakraborty, R. Venkatesh Babu

Published: 2019-12-27T02:05:45.000Z

## Abstract

In this era of digital information explosion, an abundance of data from numerous modalities is being generated as well as archived everyday. However, most problems associated with training Deep Neural Networks still revolve around lack of data that is rich enough for a given task. Data is required not only for training an initial model, but also for future learning tasks such as Model Compression and Incremental Learning. A diverse dataset may be used for training an initial model, but it may not be feasible to store it throughout the product life cycle due to data privacy issues or memory constraints. We propose to bridge the gap between the abundance of available data and lack of relevant data, for the future learning tasks of a given trained network. We use the available data, that may be an imbalanced subset of the original training dataset, or a related domain dataset, to retrieve representative samples from a trained classifier, using a novel Data-enriching GAN (DeGAN) framework. We demonstrate that data from a related domain can be leveraged to achieve state-of-the-art performance for the tasks of Data-free Knowledge Distillation and Incremental Learning on benchmark datasets. We further demonstrate that our proposed framework can enrich any data, even from unrelated domains, to make it more useful for the future learning tasks of a given network.

## 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.

- [Image Classification on CIFAR-100 (Model Cloning/Victim Accuracy)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-model-cloning-victim-accuracy.md>): Image Classification; CIFAR-100; Victim Accuracy: 78.52.

- [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): not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1912.11960>)

[PDF](<https://arxiv.org/pdf/1912.11960.pdf>)
