Strainer GAN: Filtering out Impurity Samples in GAN Training
Jiho Shin, Seungkyu Lee · 2024
Figure 1: Diagram of Strainer GAN (When trained on impure datasets, DCGAN generates undesired anomalous images, whereas our method successfully produces images consistent with the intended training data) AbstractIn practical applications of GAN for image generation, large size training samples may be collected from random databases or webpages.For example, if we collect human face images for training set it may include unexpected impure samples such as cartoon or anime human face images that hinder realistic and high quality human face generation.Manually removing such impure samples is extremely time-consuming and impractical due to the large volume of data.In this work, we propose a novel method to au-tomatically remove impure samples in GAN training.