The ubiquitous and demonstrably suboptimal choice of resizing images to ...
The most performant spatio-temporal action localisation models use exter...
The top-k operator returns a k-sparse vector, where the non-zero values
...
Transfer learning is the predominant paradigm for training deep networks...
Accurate estimation of predictive uncertainty (model calibration) is
ess...
High-quality estimates of uncertainty and robustness are crucial for num...
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...
The sorting operation is one of the most basic and commonly used buildin...
We propose a general framework for self-supervised learning of transfera...
Many recent methods for unsupervised or self-supervised representation
l...
The estimation of an f-divergence between two probability distributions ...
Despite the tremendous progress in the estimation of generative models, ...
Recently, there has been a growing interest in the problem of learning r...
We consider the problem of approximate Bayesian inference in log-supermo...