Degan: Data-enriching gan for retrieving representative samples from a trained classifier

Addepalli, S and Nayak, GK and Chakraborty, A and Babu, RV (2020) Degan: Data-enriching gan for retrieving representative samples from a trained classifier. In: AAAI 2020 - 34th AAAI Conference on Artificial Intelligence, 7 - 12 February 2020, New York, pp. 3130-3137.

PDF aaai_ 2020.pdf - Published Version Restricted to Registered users only Download (593kB) | Request a copy

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 Dataenriching GAN (DeGAN) framework. We demonstrate that data from a related domain can be leveraged to achieve stateof- 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. © 2020, Association for the Advancement of Artificial Intelligence.

Item Type:	Conference Paper
Publication:	AAAI 2020 - 34th AAAI Conference on Artificial Intelligence
Publisher:	AAAI press
Additional Information:	The copyright for this article belongs to AAAI press.
Keywords:	Benchmarking; Classification (of information); Data privacy; Deep learning; Deep neural networks; Distillation; Knowledge management; Life cycle, Benchmark datasets; Digital information; Incremental learning; Memory constraints; Model compression; Product life cycles; Representative sample; State-of-the-art performance, Arts computing
Department/Centre:	Division of Interdisciplinary Sciences > Computational and Data Sciences
Date Deposited:	07 Feb 2023 06:20
Last Modified:	07 Feb 2023 06:20
URI:	https://eprints.iisc.ac.in/id/eprint/79990

Actions (login required)

View Item