Sort by:

• Highly Influential Citations
• Citations
• Acceleration
• Velocity
• Recency

Learn More

Conditional Image Synthesis With Auxiliary Classifier GANs

• Augustus Odena, Christopher Olah, Jonathon Shlens
• ICML
• 2017

Synthesizing high resolution photorealistic images has been a long-standing challenge in machine learning. In this paper we introduce new methods for the improved training of generative adversarial… (More)

Self-Attention Generative Adversarial Networks

• Han Zhang, Ian J. Goodfellow, Dimitris N. Metaxas, Augustus Odena
• ArXiv
• 2018

In this paper, we propose the Self-Attention Generative Adversarial Network (SAGAN) which allows attention-driven, long-range dependency modeling for image generation tasks. Traditional convolutional… (More)

Realistic Evaluation of Deep Semi-Supervised Learning Algorithms

• Avital Oliver, Augustus Odena, Colin Raffel, Ekin D. Cubuk, Ian J. Goodfellow
• ArXiv
• 2018

Semi-supervised learning (SSL) provides a powerful framework for leveraging unlabeled data when labels are limited or expensive to obtain. SSL algorithms based on deep neural networks have recently… (More)

Realistic Evaluation of Semi-Supervised Learning Algorithms

• Augustus Odena, Colin Raffel, Ekin D. Cubuk, Ian J. Goodfellow
• 2018

Semi-supervised learning (SSL) provides a powerful framework for leveraging unlabeled data when labels are limited or expensive to obtain. Approaches based on deep neural networks have recently… (More)

Changing Model Behavior at Test-Time Using Reinforcement Learning

• Augustus Odena, Dieterich Lawson, Christopher Olah
• ArXiv
• 2017

Machine learning models are often used at test-time subject to constraints and trade-offs not present at training-time. A computer vision model operating on an embedded device may need to perform… (More)

Is Generator Conditioning Causally Related to GAN Performance?

• Augustus Odena, Jacob Buckman, +4 authors Ian J. Goodfellow
• ICML
• 2018

If you were to just glance at the spectra figures provided in the main text, using the log-determinant might seem like a reasonable thing to do. However, we note that (at least for the MNIST… (More)

TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing

• Augustus Odena, Ian J. Goodfellow
• ArXiv
• 2018

Machine learning models are notoriously difficult to interpret and debug. This is particularly true of neural networks. In this work, we introduce automated software testing techniques for neural… (More)

Skill Rating for Generative Models

• Catherine Olsson, Surya Bhupatiraju, Tom B. Brown, Augustus Odena, Ian J. Goodfellow
• ArXiv
• 2018

We explore a new way to evaluate generative models using insights from evaluation of competitive games between human players. We show experimentally that tournaments between generators and… (More)

Semi-Supervised Learning with Generative Adversarial Networks

• Augustus Odena
• ArXiv
• 2016

We extend Generative Adversarial Networks (GANs) to the semi-supervised context by forcing the discriminator network to output class labels. We train a generative model G and a discriminator D on a… (More)

Faster Asynchronous SGD

• Augustus Odena
• ArXiv
• 2016

Asynchronous distributed stochastic gradient descent methods have trouble converging because of stale gradients. A gradient update sent to a parameter server by a client is stale if the parameters… (More)

• ‹
• 1
• 2
• ›