Parameter and Data-Efficient Spectral StyleDCGAN

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Garg, Aryan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914736325525504
author Garg, Aryan
author_facet Garg, Aryan
contents 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 https://github.com/Aryan-Garg/StyleDCGAN.
format Preprint
id arxiv_https___arxiv_org_abs_2404_00597
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Parameter and Data-Efficient Spectral StyleDCGAN
Garg, Aryan
Computer Vision and Pattern Recognition
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 https://github.com/Aryan-Garg/StyleDCGAN.
title Parameter and Data-Efficient Spectral StyleDCGAN
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.00597