Smoothness Similarity Regularization for Few-Shot GAN Adaptation

V. Sushko, Ruyu Wang, Juergen Gall
2/14/2026

No official code found. Best implementation: JJuOn/SmoothnessSimilarity (4 stars, last commit 2024-11-29).

Abstract

The task of few-shot GAN adaptation aims to adapt a pre-trained GAN model to a small dataset with very few training images. While existing methods perform well when the dataset for pre-training is structurally similar to the target dataset, the approaches suffer from training instabilities or memorization issues when the objects in the two domains have a very different structure. To mitigate this limitation, we propose a new smoothness similarity regularization that transfers the inherently learned smoothness of the pre-trained GAN to the few-shot target domain even if the two domains are very different. We evaluate our approach by adapting an unconditional and a class-conditional GAN to diverse few-shot target domains. Our proposed method significantly outperforms prior few-shot GAN adaptation methods in the challenging case of structurally dissimilar source-target domains, while performing on par with the state of the art for similar source-target domains.

View on arXivView PDF

Code Implementations(1)

JJuOn/SmoothnessSimilarityCommunity66%

(Unofficial) [ICCV 2023] Smoothness Similarity Regularization for Few-Shot GAN Adaptation

40PythonNov 28, 20241 years ago

Similar Papers

Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learning

87% match1 repo162026

A Cross-Domain Few-Shot Learning Method Based on Domain Knowledge Mapping

86% match2025

FrugalNeRF: Fast Convergence for Extreme Few-shot Novel View Synthesis without Learned Priors

86% match1 repo152026

Few-Shot Adaptation Benchmark for Remote Sensing Vision-Language Models

85% match1 repo192025

Few-shot Image Generation via Information Transfer from the Built Geodesic Surface

85% match1 repo12024

Few and Fewer: Learning Better from Few Examples Using Fewer Base Classes

85% match2024

Cite this paper

@article{sushko2026smoothness,
  title  = {Smoothness Similarity Regularization for Few-Shot GAN Adaptation},
  author = {V. Sushko and Ruyu Wang and Juergen Gall},
  year   = {2026},
  eprint = {2308.09717},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/pdf/2308.09717},
  journal = {ICCV 2023 2023}
}

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/2308.09717.svg)](https://codeofpaper.com/paper/2308.09717)

Discussion