In this work, we introduce a self-supervised feature representation lear...
Sim2Real domain adaptation (DA) research focuses on the constrained sett...
We consider the challenging problem of outdoor lighting estimation for t...
Given a small training data set and a learning algorithm, how much more ...
Absence of large-scale labeled data in the practitioner's target domain ...
The dominant line of work in domain adaptation has focused on learning
i...
Standard Federated Learning (FL) techniques are limited to clients with
...
Autonomous driving relies on a huge volume of real-world data to be labe...
Unsupervised domain adaptation is used in many machine learning applicat...
We generalize gradient descent with momentum for learning in differentia...
Transfer learning has proven to be a successful technique to train deep
...
Current state-of-the-art methods for image segmentation form a dense ima...
Training models to high-end performance requires availability of large
l...
We tackle the problem of semantic boundary prediction, which aims to ide...
We present structured domain randomization (SDR), a variant of domain
ra...
We present a system for training deep neural networks for object detecti...
Manually labeling datasets with object masks is extremely time consuming...