paper-with-me

홈 › Papers

Conditional Augmentation for Generative Modeling

2020-01-01 · ICML 2020 1 · Heewoo Jun, Rewon Child, Mark Chen, John Schulman, Aditya Ramesh, Alec Radford, Ilya Sutskever

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationSelf-Supervised Learning

Similar Papers 제목 키워드 기반

Augmentation-Aware Self-Supervision for Data-Efficient GAN Training

2022-05-31 · NeurIPS 2023 11 · Liang Hou, Qi Cao, Yige Yuan, Songtao Zhao 외

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 Learning

Nonparametric Generative Modeling with Conditional Sliced-Wasserstein Flows

2023-05-03 · Chao Du, Tianbo Li, Tianyu Pang, Shuicheng Yan 외

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

2021-02-09 · ICLR 2021 1 · Abhishek Sinha, Kumar Ayush, Jiaming Song, Burak Uzkent 외

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+9

Turning Waste into Wealth: Leveraging Low-Quality Samples for Enhancing Continuous Conditional Generative Adversarial Networks

2023-08-20 · Xin Ding, Yongwei Wang, Zuheng Xu

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 Augmentation

Is Conditional Generative Modeling all you need for Decision-Making?

2022-11-28 · Anurag Ajay, Yilun Du, Abhi Gupta, Joshua Tenenbaum 외

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