24 citations · 86 across the 21 of their papers we have counts for
8 papers · 1 filter
Ensembling Off-the-shelf Models for GAN Training
Nupur Kumari, Richard Zhang, Eli Shechtman +1
The advent of large-scale training has produced a cornucopia of powerful visual recognition models. However, generative models, such as GANs, have traditionally been trained from s…
GAN-Supervised Dense Visual Alignment
William Peebles, Jun-Yan Zhu, Richard Zhang +3
We propose GAN-Supervised Learning, a framework for learning discriminative models and their GAN-generated training data jointly end-to-end. We apply our framework to the dense vis…
Contrastive Feature Loss for Image Prediction
Alex Andonian, Taesung Park, Bryan Russell +3
Training supervised image synthesis models requires a critic to compare two images: the ground truth to the result. Yet, this basic functionality remains an open problem. A popular…
Editing Conditional Radiance Fields
Steven Liu, Xiuming Zhang, Zhoutong Zhang +3
A neural radiance field (NeRF) is a scene model supporting high-quality view synthesis, optimized per scene. In this paper, we explore enabling user editing of a category-level NeR…
Ensembling with Deep Generative Views
Lucy Chai, Jun-Yan Zhu, Eli Shechtman +2
Recent generative models can synthesize "views" of artificial images that mimic real-world variations, such as changes in color or pose, simply by learning from unlabeled image col…
Few-shot Image Generation via Cross-domain Correspondence
Utkarsh Ojha, Yijun Li, Jingwan Lu +4
Training generative models, such as GANs, on a target domain containing limited examples (e.g., 10) can easily result in overfitting. In this work, we seek to utilize a large sourc…
On Aliased Resizing and Surprising Subtleties in GAN Evaluation
Gaurav Parmar, Richard Zhang, Jun-Yan Zhu
Metrics for evaluating generative models aim to measure the discrepancy between real and generated images. The often-used Frechet Inception Distance (FID) metric, for example, extr…
The Low-Rank Simplicity Bias in Deep Networks
Minyoung Huh, Hossein Mobahi, Richard Zhang +3
Modern deep neural networks are highly over-parameterized compared to the data on which they are trained, yet they often generalize remarkably well. A flurry of recent work has ask…