Regression Networks for Meta-Learning Few-Shot Classification

Understand

We propose regression networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each class.

• In high dimensional embedding spaces the direction of data generally contains richer information than magnitude.
• Next to this, state-of-the-art few-shot metric methods that compare distances with aggregated class representations, have shown superior performance.
• Combining these two insights, we propose to meta-learn classification of embedded points by regressing the closest approximation in every class subspace while using the regression error as a distance metric.