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

TL;DR

DeGAN is a novel framework that uses a data-enriching GAN to retrieve and generate representative samples from a trained classifier, improving data efficiency for future learning tasks like knowledge distillation and incremental learning.

Contribution

The paper introduces DeGAN, a new GAN-based method for retrieving and enriching data relevant to a trained classifier, even from unrelated domains, to enhance future learning tasks.

Findings

Achieves state-of-the-art performance in data-free knowledge distillation.

Effectively retrieves representative samples from imbalanced or related datasets.

Enriches unrelated domain data to improve model training and adaptation.

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.