Class-Splitting Generative Adversarial Networks
Generative Adversarial Networks (GANs) produce systematically better quality samples when class label information is provided., i.e. in the conditional GAN setup. This is still observed for the recently proposed Wasserstein GAN formulation which stabilized adversarial training and allows considering high capacity network architectures such as ResNet. In this work we show how to boost conditional GAN by augmenting available class labels. The new classes come from clustering in the representation space learned by the same GAN model. The proposed strategy is also feasible when no class information is available, i.e. in the unsupervised setup. Our generated samples reach state-of-the-art Inception scores for CIFAR-10 and STL-10 datasets in both supervised and unsupervised setup.
Code (1)
Tasks
ClusteringConditional Image GenerationImage GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
GANISP: a GAN-assisted Importance SPlitting Probability Estimator
Designing manufacturing processes with high yield and strong reliability relies on effective methods for rare event estimation. Genealogical importance splitting reduces the variance of rare event probability estimators …
Generative Adversarial NetworkAdapt & Align: Continual Learning with Generative Models Latent Space Alignment
In this work, we introduce Adapt & Align, a method for continual learning of neural networks by aligning latent representations in generative models. Neural Networks suffer from abrupt loss in performance when retrained …
Continual LearningProximal Splitting Adversarial Attacks for Semantic Segmentation
Classification has been the focal point of research on adversarial attacks, but only a few works investigate methods suited to denser prediction tasks, such as semantic segmentation. The methods proposed in these works d…
Adversarial AttackSegmentationSemantic SegmentationProximal Splitting Adversarial Attack for Semantic Segmentation
Classification has been the focal point of research on adversarial attacks, but only a few works investigate methods suited to denser prediction tasks, such as semantic segmentation. The methods proposed in these wor…
Adversarial AttackSegmentationSemantic SegmentationPredictive GAN-powered Multi-Objective Optimization for Hybrid Federated Split Learning
As an edge intelligence algorithm for multi-device collaborative training, federated learning (FL) can reduce the communication burden but increase the computing load of wireless devices. In contrast, split learning (SL)…
Federated LearningGenerative Adversarial Network