Top-k Training of GANs: Improving GAN Performance by Throwing Away Bad Samples
원문 초록
We introduce a simple (one line of code) modification to the Generative Adversarial Network (GAN) training algorithm that materially improves results with no increase in computational cost: When updating the generator parameters, we simply zero out the gradient contributions from the elements of the batch that the critic scores as `least realistic'. Through experiments on many different GAN variants, we show that this `top-k update' procedure is a generally applicable improvement. In order to understand the nature of the improvement, we conduct extensive analysis on a simple mixture-of-Gaussians dataset and discover several interesting phenomena. Among these is that, when gradient updates are computed using the worst-scoring batch elements, samples can actually be pushed further away from their nearest mode. We also apply our method to recent GAN variants and improve state-of-the-art FID for conditional generation from 9.21 to 8.57 on CIFAR-10.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Generative Latent Kernel Modeling for Blind Motion Deblurring
ReflectGAN: Modeling Vegetation Effects for Soil Carbon Estimation from Satellite Imagery
ROIsGAN: A Region Guided Generative Adversarial Framework for Murine Hippocampal Subregion Segmentation
Unsupervised Raindrop Removal from a Single Image using Conditional Diffusion Models
DeeCLIP: A Robust and Generalizable Transformer-Based Framework for Detecting AI-Generated Images
Performance of Machine Learning Classifiers for Anomaly Detection in Cyber Security Applications
토론
이 논문과 연결된 포럼 글이 아직 없습니다.