A Theoretical Analysis of the Number of Shots in Few-Shot Learning

Tianshi Cao, Marc T Law, Sanja Fidler

TL;DR: The paper analyzes the effect of shot number on prototypical networks and proposes a robust method when the shot number differs from meta-training to meta-testing time.

Abstract: Few-shot classification is the task of predicting the category of an example from a set of few labeled examples. The number of labeled examples per category is called the number of shots (or shot number). Recent works tackle this task through meta-learning, where a meta-learner extracts information from observed tasks during meta-training to quickly adapt to new tasks during meta-testing. In this formulation, the number of shots exploited during meta-training has an impact on the recognition performance at meta-test time. Generally, the shot number used in meta-training should match the one used in meta-testing to obtain the best performance. We introduce a theoretical analysis of the impact of the shot number on Prototypical Networks, a state-of-the-art few-shot classification method. From our analysis, we propose a simple method that is robust to the choice of shot number used during meta-training, which is a crucial hyperparameter. The performance of our model trained for an arbitrary meta-training shot number shows great performance for different values of meta-testing shot numbers. We experimentally demonstrate our approach on different few-shot classification benchmarks.

Keywords: Few shot learning, Meta Learning, Performance Bounds

Data: [mini-Imagenet](https://paperswithcode.com/dataset/mini-imagenet), [tieredImageNet](https://paperswithcode.com/dataset/tieredimagenet)