# Regression Networks for Meta-Learning Few-Shot Classification

arXiv: https://arxiv.org/abs/1905.13613 · HTML: https://mlsanity.com/paper/1905.13613/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 May 2019.

## Built on by (most cited first, 1 of 1)

- [Self-Taught Semi-Supervised Anomaly Detection on Upper Limb X-rays](https://mlsanity.com/paper/2102.09895/) (2021)

## Abstract (arXiv)

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. Similarly to recent approaches for few-shot learning, regression networks reflect a simple inductive bias that is beneficial in this limited-data regime and they achieve excellent results, especially when more aggregate class representations can be formed with multiple shots.