Few-Shot Learning with Embedded Class Models and Shot-Free Meta Training
This addresses the problem of flexible few-shot learning for AI systems that need to handle variable numbers of classes and shots, though it appears incremental in its methodological contributions.
The paper tackles few-shot learning by proposing embedded class models with shot-free meta training, which learns class prototypes in a higher-dimensional space rather than using Euclidean averages. This approach achieves state-of-the-art performance on standard few-shot benchmark datasets.
We propose a method for learning embeddings for few-shot learning that is suitable for use with any number of ways and any number of shots (shot-free). Rather than fixing the class prototypes to be the Euclidean average of sample embeddings, we allow them to live in a higher-dimensional space (embedded class models) and learn the prototypes along with the model parameters. The class representation function is defined implicitly, which allows us to deal with a variable number of shots per each class with a simple constant-size architecture. The class embedding encompasses metric learning, that facilitates adding new classes without crowding the class representation space. Despite being general and not tuned to the benchmark, our approach achieves state-of-the-art performance on the standard few-shot benchmark datasets.