Parameter and Data Efficient Spectral Style-DCGAN

Published: 19 Mar 2024, Last Modified: 31 Mar 2024Tiny Papers @ ICLR 2024 NotableEveryoneRevisionsBibTeXCC BY 4.0
Keywords: Generative modeling, unconditional generation, data efficient, parameter efficient, machine learning, animal face generation
TL;DR: A simple, highly parameter, and data-efficient adversarial network for unconditional animal face generation
Abstract: We present a simple, highly parameter, and data-efficient adversarial network for unconditional face generation. Our method: Spectral Style-DCGAN or SSD utilizes only 6.574 million parameters and 4739 dog faces from the Animal Faces HQ (AFHQ) dataset as training samples while preserving fidelity at low resolutions up to 64x64. Code available at Anonymous-repo.
Submission Number: 22
Loading