ScaleFace: Uncertainty-aware Deep Metric Learning. (arXiv:2209.01880v2 [cs.CV] UPDATED)

The performance of modern deep learning-based systems dramatically depends on
the quality of input objects. For example, face recognition quality would be
lower for blurry or corrupted inputs. However, it is hard to predict the
influence of input quality on the resulting accuracy in more complex scenarios.
We propose an approach for deep metric learning that allows direct estimation
of the uncertainty with almost no additional computational cost. The developed
\textit{ScaleFace} algorithm uses trainable scale values that modify
similarities in …

arxiv uncertainty