activity
20122022
most citedCyCADA: Cycle-Consistent Adversarial Domain Adaptation

630 citations · 2.3k across the 46 of their papers we have counts for

collaborators
Showing cs.CVShow all

69 papers · 1 filter

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.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.CV2021

Strumming to the Beat: Audio-Conditioned Contrastive Video Textures

Medhini Narasimhan, Shiry Ginosar, Andrew Owens +2

We introduce a non-parametric approach for infinite video texture synthesis using a representation learned via contrastive learning. We take inspiration from Video Textures, which…

cs.CV2021

Robust Object Detection via Instance-Level Temporal Cycle Confusion

Xin Wang, Thomas E. Huang, Benlin Liu +4

Building reliable object detectors that are robust to domain shifts, such as various changes in context, viewpoint, and object appearances, is critical for real-world applications.…

cs.CV2021

NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media

Grace Luo, Trevor Darrell, Anna Rohrbach

Online misinformation is a prevalent societal issue, with adversaries relying on tools ranging from cheap fakes to sophisticated deep fakes. We are motivated by the threat scenario…