Augustus Odena

Publications30
h-index19
Citations6,870
Highly Influential Citations865
Claim Author Page
Author pages are created from data sourced from our academic publisher partnerships and public sources.

Recommended Authors

  • Ian J. Goodfellow
  • 114 Publications • 125,670 Citations
  • Yoshua Bengio
  • 844 Publications • 352,583 Citations
  • Ilya Sutskever
  • 97 Publications • 220,007 Citations
  • Alec Radford
  • 29 Publications • 38,204 Citations
  • Publications
  • Influence
Conditional Image Synthesis with Auxiliary Classifier GANs
TLDR
A variant of GANs employing label conditioning that results in 128 x 128 resolution image samples exhibiting global coherence is constructed and it is demonstrated that high resolution samples provide class information not present in low resolution samples.
Self-Attention Generative Adversarial Networks
TLDR
The proposed SAGAN achieves the state-of-the-art results, boosting the best published Inception score from 36.8 to 52.52 and reducing Frechet Inception distance from 27.62 to 18.65 on the challenging ImageNet dataset.
Realistic Evaluation of Deep Semi-Supervised Learning Algorithms
TLDR
This work creates a unified reimplemention and evaluation platform of various widely-used SSL techniques and finds that the performance of simple baselines which do not use unlabeled data is often underreported, that SSL methods differ in sensitivity to the amount of labeled and unlabeling data, and that performance can degrade substantially when the unlabelED dataset contains out-of-class examples.
Semi-Supervised Learning with Generative Adversarial Networks
TLDR
This work extends Generative Adversarial Networks to the semi-supervised context by forcing the discriminator network to output class labels and shows that this method can be used to create a more data-efficient classifier and that it allows for generating higher quality samples than a regular GAN.
Deconvolution and Checkerboard Artifacts
Consistency Regularization for Generative Adversarial Networks
TLDR
This work proposes a simple, effective training stabilizer based on the notion of consistency regularization, which improves state-of-the-art FID scores for conditional generation and achieves the best F ID scores for unconditional image generation compared to other regularization methods on CIFAR-10 and CelebA.
Discriminator Rejection Sampling
TLDR
A rejection sampling scheme using the discriminator of a GAN to approximately correct errors in the GAN generator distribution and a practical algorithm - called Discriminator Rejection Sampling (DRS) - that can be used on real data-sets is designed.
TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing
TLDR
This work develops coverage-guided fuzzing methods for neural networks that are well-suited to discovering errors which occur only for rare inputs, and describes how fast approximate nearest neighbor algorithms can provide this coverage metric.
Improved Consistency Regularization for GANs
TLDR
This work shows that consistency regularization can introduce artifacts into the GAN samples and proposes several modifications to the consistencyRegularization procedure designed to improve its performance, and yields the best known FID scores on various GAN architectures.
Realistic Evaluation of Semi-Supervised Learning Algorithms
TLDR
This work creates a unified reimplemention and evaluation platform of various widelyused SSL techniques and finds that the performance of simple baselines which do not use unlabeled data is often underreported, that SSL methods differ in sensitivity to the amount of labeled and unlabeling data, and that performance can degrade substantially when the unlabelED dataset contains out-of-class examples.
...
1
2
3
...