Data InStance Prior (DISP) in Generative Adversarial Networks

Mangla, Puneet and Kumari, Nupur and Singh, Mayank and Krishnamurthy, Balaji and Balasubramanian, Vineeth N (2022) Data InStance Prior (DISP) in Generative Adversarial Networks. In: 22nd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022, 4 January 2022 through 8 January 2022, Waikoloa.

Text
Proceedings_2022_IEEE_CVF.pdf - Published Version
Available under License Creative Commons Attribution.
Download (1MB)

Abstract

Recent advances in generative adversarial networks (GANs) have shown remarkable progress in generating high-quality images. However, this gain in performance depends on the availability of a large amount of training data. In limited data regimes, training typically diverges, and therefore the generated samples are of low quality and lack diversity. Previous works have addressed training in low data setting by leveraging transfer learning and data augmentation techniques. We propose a novel transfer learning method for GANs in the limited data domain by leveraging informative data prior derived from self-supervised/supervised pre-trained networks trained on a diverse source domain. We perform experiments on several standard vision datasets using various GAN architectures (BigGAN, SNGAN, StyleGAN2) to demonstrate that the proposed method effectively transfers knowledge to domains with few target images, outperforming existing state-of-the-art techniques in terms of image quality and diversity. We also show the utility of data instance prior in large-scale unconditional image generation. © 2022 IEEE.

[error in script]

IITH Creators:

IITH Creators	ORCiD
Balasubramanian, Vineeth N	https://orcid.org/0000-0003-2656-0375

Item Type:

Conference or Workshop Item (Paper)

Uncontrolled Keywords:

Autoencoders; Deep Learning; Deep Learning Datasets; Evaluation and Comparison of Vision Algorithms; Few-shot; GANs; Neural Generative Models; Semi- and Un- supervised Learning; Transfer

Subjects:

Computer science

Divisions:

Department of Computer Science & Engineering

Depositing User:

. LibTrainee 2021

Date Deposited:

28 Jul 2022 09:15

Last Modified:

28 Jul 2022 09:15

URI:

http://raiithold.iith.ac.in/id/eprint/9985