# Boosting Few-Shot Visual Learning with Self-Supervision

## TL;DR

This paper presents a method that combines self-supervised learning with few-shot learning to improve the quality of visual representations, enabling better performance with limited labeled data and leveraging unlabeled data effectively.

## Contribution

It introduces a novel approach that uses self-supervision as an auxiliary task in few-shot learning, enhancing feature transferability and performance across various datasets and architectures.

## Key findings

- Consistent performance improvements across multiple datasets.
- Enhanced feature transferability due to self-supervised auxiliary tasks.
- Ability to incorporate unlabeled data from different datasets.

## Abstract

Few-shot learning and self-supervised learning address different facets of the same problem: how to train a model with little or no labeled data. Few-shot learning aims for optimization methods and models that can learn efficiently to recognize patterns in the low data regime. Self-supervised learning focuses instead on unlabeled data and looks into it for the supervisory signal to feed high capacity deep neural networks. In this work we exploit the complementarity of these two domains and propose an approach for improving few-shot learning through self-supervision. We use self-supervision as an auxiliary task in a few-shot learning pipeline, enabling feature extractors to learn richer and more transferable visual representations while still using few annotated samples. Through self-supervision, our approach can be naturally extended towards using diverse unlabeled data from other datasets in the few-shot setting. We report consistent improvements across an array of architectures, datasets and self-supervision techniques.