We introduce Three Towers (3T), a flexible method to improve the contras...
Leveraging privileged information (PI), or features available during tra...
Heteroscedastic classifiers, which learn a multivariate Gaussian distrib...
We introduce Inkorrect, a data- and label-efficient approach for online
...
Supervised learning datasets often have privileged information, in the f...
Uncertainty estimation in deep learning has recently emerged as a crucia...
Large scale image classification datasets often contain noisy labels. We...
The core challenge with continual learning is catastrophic forgetting, t...
Modelling uncertainty arising from input-dependent label noise is an
inc...
Neural architecture search has recently attracted lots of research effor...
This paper proposes a novel per-task routing method for multi-task
appli...
Learning to localize and name object instances is a fundamental problem ...
Neural architecture search has been shown to hold great promise towards ...
To alleviate the cost of obtaining accurate bounding boxes for training
...
We present the 2017 WebVision Challenge, a public image recognition chal...