574 citations · 585 across the 5 of their papers we have counts for
4 papers · 1 filter
VisDA-2021 Competition Universal Domain Adaptation to Improve Performance on Out-of-Distribution Data
Dina Bashkirova, Dan Hendrycks, Donghyun Kim +5
Progress in machine learning is typically measured by training and testing a model on the same distribution of data, i.e., the same domain. This over-estimates future accuracy on o…
Log-Likelihood Ratio Minimizing Flows: Towards Robust and Quantifiable Neural Distribution Alignment
Ben Usman, Avneesh Sud, Nick Dufour +1
Distribution alignment has many applications in deep learning, including domain adaptation and unsupervised image-to-image translation. Most prior work on unsupervised distribution…
Cross-Domain Image Manipulation by Demonstration
Ben Usman, Nick Dufour, Kate Saenko +1
In this work we propose a model that can manipulate individual visual attributes of objects in a real scene using examples of how respective attribute manipulations affect the outp…
Stable Distribution Alignment Using the Dual of the Adversarial Distance
Ben Usman, Kate Saenko, Brian Kulis
Methods that align distributions by minimizing an adversarial distance between them have recently achieved impressive results. However, these approaches are difficult to optimize w…