Supplementary Material: Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval

Let X be the data space, Z be the latent space, be the parameter space. A dataset is a collection of data point-class pairs (x, c) 2X C. D = {(x In the metric learning setting, instead of enforcing properties of a single data point, the goal is to enforce relations between data points. The target, or label, is the value that encodes the information we want to learn. In classical settings, we have one scalar for each data point: a class for classification, a value for regression. This definition is intuitive and compact, but not formal enough to show that the contrastive loss is in fact an unnormalized log posterior.