205 citations · 220 across the 2 of their papers we have counts for
2 papers
stat.ML2020★ 15 cited
Top-k Training of GANs: Improving GAN Performance by Throwing Away Bad Samples
Samarth Sinha, Zhengli Zhao, Anirudh Goyal +2
We introduce a simple (one line of code) modification to the Generative Adversarial Network (GAN) training algorithm that materially improves results with no increase in computatio…
cs.LG2018★ 205 cited
Realistic Evaluation of Deep Semi-Supervised Learning Algorithms
Avital Oliver, Augustus Odena, Colin Raffel +2
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 netwo…