# Few-Shot Learning with Embedded Class Models and Shot-Free Meta Training

## TL;DR

This paper introduces a flexible few-shot learning method that learns embedded class models in a higher-dimensional space, enabling shot-free training and superior performance across various datasets.

## Contribution

It presents a novel approach that learns class prototypes in an embedded space and handles variable shots, improving adaptability and accuracy in few-shot learning.

## Key findings

- Achieves state-of-the-art results on standard few-shot benchmarks.
- Handles any number of classes and shots without retraining.
- Enables adding new classes easily through metric learning.

## Abstract

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.