Parameter and Data-Efficient Spectral StyleDCGAN

Aryan Garg
3/31/2024
cs.CV

No confident code implementation found for this paper.

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 https://github.com/Aryan-Garg/StyleDCGAN.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

A Style-Based Generator Architecture for Generative Adversarial Networks

83% match2 repos14.4k2018

Non-Adaptive Adversarial Face Generation

81% match2025

Parameter Efficient Local Implicit Image Function Network for Face Segmentation

81% match2026

Single Image, Any Face: Generalisable 3D Face Generation

80% match2024

Controllable Adversarial Makeup for Privacy via Text-Guided Diffusion

79% match2025

SISMA: Semantic Face Image Synthesis with Mamba

79% match2025

Cite this paper

@article{garg2024parameter,
  title  = {Parameter and Data-Efficient Spectral StyleDCGAN},
  author = {Aryan Garg},
  year   = {2024},
  eprint = {2404.00597},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2404.00597v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2404.00597.svg)](https://codeofpaper.com/paper/2404.00597)

Discussion