Search Results for author:
Found 1 papers, 1 papers with code
No Fuss Distance Metric Learning using Proxies
Traditionally, for this problem supervision is expressed in the form of sets of points that follow an ordinal relationship -- an anchor point $x$ is similar to a set of positive points $Y$, and dissimilar to a set of negative points $Z$, and a loss defined over these distances is minimized.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
