Improving the Effectiveness of Deep Generative Data

no code implementations • 7 Nov 2023 • Ruyu Wang, Sabrina Schmedding, Marco F. Huber

Although looking appealing to human eyes, training a model on purely synthetic images for downstream image processing tasks like image classification often results in an undesired performance drop compared to training on real data.

Data Augmentation Image Classification

Smoothness Similarity Regularization for Few-Shot GAN Adaptation

no code implementations • ICCV 2023 • Vadim Sushko, Ruyu Wang, Juergen Gall

The task of few-shot GAN adaptation aims to adapt a pre-trained GAN model to a small dataset with very few training images.

Memorization

Defect Transfer GAN: Diverse Defect Synthesis for Data Augmentation

no code implementations • 16 Feb 2023 • Ruyu Wang, Sabrina Hoppe, Eduardo Monari, Marco F. Huber

Data-hunger and data-imbalance are two major pitfalls in many deep learning approaches.

Data Augmentation Image Generation