activity
20122023
most citedCyCADA: Cycle-Consistent Adversarial Domain Adaptation

630 citations · 2.3k across the 52 of their papers we have counts for

collaborators
Showing 2021Show all

15 papers · 1 filter

cs.CL20211 cited

Discovering Non-monotonic Autoregressive Orderings with Variational Inference

Xuanlin Li, Brandon Trabucco, Dong Huk Park +4

The predominant approach for language modeling is to process sequences from left to right, but this eliminates a source of information: the order by which the sequence was generate…

cs.CV2021

On-target Adaptation

Dequan Wang, Shaoteng Liu, Sayna Ebrahimi +2

Domain adaptation seeks to mitigate the shift between training on the \emph{source} domain and testing on the \emph{target} domain. Most adaptation methods rely on the source data…

cs.CV2021

Tune it the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Density

Kuniaki Saito, Donghyun Kim, Piotr Teterwak +3

Unsupervised domain adaptation (UDA) methods can dramatically improve generalization on unlabeled target domains. However, optimal hyper-parameter selection is critical to achievin…

cs.LG2021

Predicting with Confidence on Unseen Distributions

Devin Guillory, Vaishaal Shankar, Sayna Ebrahimi +2

Recent work has shown that the performance of machine learning models can vary substantially when models are evaluated on data drawn from a distribution that is close to but differ…

cs.CV2021353 cited

Early Convolutions Help Transformers See Better

Tete Xiao, Mannat Singh, Eric Mintun +3

Vision transformer (ViT) models exhibit substandard optimizability. In particular, they are sensitive to the choice of optimizer (AdamW vs. SGD), optimizer hyperparameters, and tra…

cs.RO20214 cited

Auto-Tuned Sim-to-Real Transfer

Yuqing Du, Olivia Watkins, Trevor Darrell +2

Policies trained in simulation often fail when transferred to the real world due to the `reality gap' where the simulator is unable to accurately capture the dynamics and visual pr…