Transfer learning is the predominant paradigm for training deep networks...
We investigate the impact of aliasing on generalization in Deep Convolut...
Accurate estimation of predictive uncertainty (model calibration) is
ess...
Before deploying machine learning models it is critical to assess their
...
We propose a method to learn image representations from uncurated videos...
Modern deep convolutional networks (CNNs) are often criticized for not
g...
Training convolutional networks for semantic segmentation with strong
(p...
We propose a normalization layer for unsupervised domain adaption in sem...
Data analytics helps basketball teams to create tactics. However, manual...
One of the emerging trends for sports analytics is the growing use of pl...