70 citations · 70 across the 1 of their papers we have counts for
5 papers
You Only Need Adversarial Supervision for Semantic Image Synthesis
Vadim Sushko, Edgar Schönfeld, Dan Zhang +3
Despite their recent successes, GAN models for semantic image synthesis still suffer from poor image quality when trained with only adversarial supervision. Historically, additiona…
Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Features
Robin Tibor Schirrmeister, Yuxuan Zhou, Tonio Ball +1
Deep generative networks trained via maximum likelihood on a natural image dataset like CIFAR10 often assign high likelihoods to images from datasets with different objects (e.g.,…
On-manifold Adversarial Data Augmentation Improves Uncertainty Calibration
Kanil Patel, William Beluch, Dan Zhang +2
Uncertainty estimates help to identify ambiguous, novel, or anomalous inputs, but the reliable quantification of uncertainty has proven to be challenging for modern deep networks.…
Group Pruning using a Bounded-Lp norm for Group Gating and Regularization
Chaithanya Kumar Mummadi, Tim Genewein, Dan Zhang +2
Deep neural networks achieve state-of-the-art results on several tasks while increasing in complexity. It has been shown that neural networks can be pruned during training by impos…
Progressive Augmentation of GANs
Dan Zhang, Anna Khoreva
Training of Generative Adversarial Networks (GANs) is notoriously fragile, requiring to maintain a careful balance between the generator and the discriminator in order to perform w…