Conditional Augmentation for Generative Modeling
We present conditional augmentation (CondAugment), a simple and powerful method of regularizing generative models. Core to our approach is applying augmentation functions to data and then conditioning the generative model on the specific function used. Unlike typical data augmentation, CondAugment allows usage of functions which modify the target density, enabling aggressive augmentations more commonly seen in supervised and self-supervised learning. We demonstrate this is a more effective regularizer than standard methods, and use it to train a 150M parameter autoregressive model on CIFAR-10 to 2.56 bits per dim (relative to the state-of-the-art 2.80). Samples from this model attain FID 12.75 and IS 8.40, outperforming the majority of GANs. We further demonstrate the technique is broadly applicable across model architectures, objectives, and problem domains.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationSelf-Supervised LearningSimilar Papers 제목 키워드 기반
Augmentation-Aware Self-Supervision for Data-Efficient GAN Training
Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting. Previously proposed differentiable augmentation demonstrates improved data efficiency of…
Data AugmentationRepresentation LearningNonparametric Generative Modeling with Conditional Sliced-Wasserstein Flows
Sliced-Wasserstein Flow (SWF) is a promising approach to nonparametric generative modeling but has not been widely adopted due to its suboptimal generative quality and lack of conditional modeling capabilities. In this w…
Negative Data Augmentation
Data augmentation is often used to enlarge datasets with synthetic samples generated in accordance with the underlying data distribution. To enable a wider range of augmentations, we explore negative data augmentation st…
Action RecognitionAnomaly DetectionConditional Image GenerationContrastive Learning+9Turning Waste into Wealth: Leveraging Low-Quality Samples for Enhancing Continuous Conditional Generative Adversarial Networks
Continuous Conditional Generative Adversarial Networks (CcGANs) enable generative modeling conditional on continuous scalar variables (termed regression labels). However, they can produce subpar fake images due to limite…
Data AugmentationIs Conditional Generative Modeling all you need for Decision-Making?
Recent improvements in conditional generative modeling have made it possible to generate high-quality images from language descriptions alone. We investigate whether these methods can directly address the problem of sequ…
AllDecision MakingOffline RLReinforcement Learning (RL)+1