Diagnosing and Remedying Shot Sensitivity with Cosine Few-Shot Learners

TL;DR

This paper investigates shot sensitivity in few-shot learning, revealing that cosine-based classifiers significantly improve robustness to shot variation and outperform existing methods across various benchmarks.

Contribution

It introduces cosine distance-based classifiers that enhance shot robustness in few-shot learning, broadening applicability and outperforming prior methods.

Findings

Cosine classifiers improve shot robustness across architectures.

Larger neural models show inherent robustness to shot variation.

Cosine-based methods outperform prior shot-robust approaches.

Abstract

Few-shot recognition involves training an image classifier to distinguish novel concepts at test time using few examples (shot). Existing approaches generally assume that the shot number at test time is known in advance. This is not realistic, and the performance of a popular and foundational method has been shown to suffer when train and test shots do not match. We conduct a systematic empirical study of this phenomenon. In line with prior work, we find that shot sensitivity is broadly present across metric-based few-shot learners, but in contrast to prior work, larger neural architectures provide a degree of built-in robustness to varying test shot. More importantly, a simple, previously known but greatly overlooked class of approaches based on cosine distance consistently and greatly improves robustness to shot variation, by removing sensitivity to sample noise. We derive cosine alternatives to popular and recent few-shot classifiers, broadening their applicability to realistic settings. These cosine models consistently improve shot-robustness, outperform prior shot-robust state of the art, and provide competitive accuracy on a range of benchmarks and architectures, including notable gains in the very-low-shot regime.