GAN Generator
GAN generators are neural networks designed to synthesize realistic data, primarily images, by learning the underlying distribution of a training dataset. Current research emphasizes improving the controllability and fidelity of generated data, focusing on architectures like StyleGAN and incorporating techniques such as wavelet transforms for efficient feature extraction and latent space manipulation for targeted image editing. These advancements are significant for applications ranging from medical image generation to augmenting datasets for downstream tasks like image segmentation and anomaly detection, ultimately addressing data scarcity and improving the performance of various computer vision models.
Papers
February 22, 2024
December 10, 2023
November 9, 2023
June 19, 2023
March 10, 2023
February 4, 2023
January 12, 2023
January 11, 2023
December 8, 2022
November 6, 2022
September 5, 2022
August 25, 2022
August 18, 2022
August 3, 2022
June 9, 2022
May 5, 2022
April 5, 2022
February 21, 2022