Feature Representation in Deep Metric Embeddings

no code implementations • 5 Feb 2021 • Ryan Furlong, Vincent O'Brien, James Garland, Daniel Palacios-Alonso, Francisco Dominguez-Mateos

In deep metric learning (DML), high-level input data are represented in a lower-level representation (embedding) space, such that samples from the same class are mapped close together, while samples from disparate classes are mapped further apart.

Few-Shot Learning Metric Learning