Modeling the effect of sequence variation on function is a fundamental problem for
understanding and designing proteins. Since evolution encodes information about function …

Letting a deep network be aware of the quality of its own predictions is an interesting yet
important problem. In the task of instance segmentation, the confidence of instance …

Deep neural networks have attained remarkable performance when applied to data that
comes from the same distribution as that of the training set, but can significantly degrade …

Neural networks predictions are unreliable when the input sample is out of the training
distribution or corrupted by noise. Being able to detect such failures automatically is …

Assessing reliably the confidence of a deep neural net and predicting its failures is of
primary importance for the practical deployment of these models. In this paper, we propose a …

Despite the power of deep neural networks for a wide range of tasks, an overconfident
prediction issue has limited their practical use in many safety-critical applications. Many …

Modern face alignment methods have become quite accurate at predicting the locations of
facial landmarks, but they do not typically estimate the uncertainty of their predicted locations …

Learning to reject is a special kind of self-awareness (the ability to know what you do not
know), which is an essential factor for humans to become smarter. Although machine …

Aleatoric uncertainty captures noise within the observations. For camouflaged object
detection, due to similar appearance of the camouflaged foreground and the background, it's …

Unbiased confidence estimates of neural networks are crucial especially for safety-critical
applications. Many methods have been developed to calibrate biased confidence estimates …