Scalable Diffusion Models with Transformers

7 code implementations • ICCV 2023 • William Peebles, Saining Xie

We explore a new class of diffusion models based on the transformer architecture.

Image Generation

Learning to Learn with Generative Models of Neural Network Checkpoints

1 code implementation • 26 Sep 2022 • William Peebles, Ilija Radosavovic, Tim Brooks, Alexei A. Efros, Jitendra Malik

We explore a data-driven approach for learning to optimize neural networks.

GAN-Supervised Dense Visual Alignment

1 code implementation • CVPR 2022 • William Peebles, Jun-Yan Zhu, Richard Zhang, Antonio Torralba, Alexei A. Efros, Eli Shechtman

We propose GAN-Supervised Learning, a framework for learning discriminative models and their GAN-generated training data jointly end-to-end.

Data Augmentation Dense Pixel Correspondence Estimation

The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement

1 code implementation • ECCV 2020 • William Peebles, John Peebles, Jun-Yan Zhu, Alexei Efros, Antonio Torralba

In this paper, we propose the Hessian Penalty, a simple regularization term that encourages the Hessian of a generative model with respect to its input to be diagonal.

Disentanglement

Semantic Photo Manipulation with a Generative Image Prior

1 code implementation • 15 May 2020 • David Bau, Hendrik Strobelt, William Peebles, Jonas Wulff, Bolei Zhou, Jun-Yan Zhu, Antonio Torralba

First, it is hard for GANs to precisely reproduce an input image.

Seeing What a GAN Cannot Generate

1 code implementation • ICCV 2019 • David Bau, Jun-Yan Zhu, Jonas Wulff, William Peebles, Hendrik Strobelt, Bolei Zhou, Antonio Torralba

Differences in statistics reveal object classes that are omitted by a GAN.

Semantic Segmentation