47 citations · 145 across the 10 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2020
SMYRF: Efficient Attention using Asymmetric Clustering
Giannis Daras, Nikita Kitaev, Augustus Odena +1
We propose a novel type of balanced clustering algorithm to approximate attention. Attention complexity is reduced from to , where is the sequence length.…
cs.LG2019
Your Local GAN: Designing Two Dimensional Local Attention Mechanisms for Generative Models
Giannis Daras, Augustus Odena, Han Zhang +1
We introduce a new local sparse attention layer that preserves two-dimensional geometry and locality. We show that by just replacing the dense attention layer of SAGAN with our con…
cs.LG2019★ 47 cited
Consistency Regularization for Generative Adversarial Networks
Han Zhang, Zizhao Zhang, Augustus Odena +1
Generative Adversarial Networks (GANs) are known to be difficult to train, despite considerable research effort. Several regularization techniques for stabilizing training have bee…