RNNP: A Robust Few-Shot Learning Approach

TL;DR

This paper introduces RNNP, a robust few-shot learning method that refines class prototypes to handle label noise in support examples, significantly improving performance under label corruption.

Contribution

The paper proposes a novel prototype refinement technique that enhances robustness of few-shot classifiers against label noise, applicable as a drop-in replacement for existing methods.

Findings

Significant performance gains under label corruption.

Robust prototypes improve classification accuracy.

Method outperforms standard few-shot approaches in noisy settings.

Abstract

Learning from a few examples is an important practical aspect of training classifiers. Various works have examined this aspect quite well. However, all existing approaches assume that the few examples provided are always correctly labeled. This is a strong assumption, especially if one considers the current techniques for labeling using crowd-based labeling services. We address this issue by proposing a novel robust few-shot learning approach. Our method relies on generating robust prototypes from a set of few examples. Specifically, our method refines the class prototypes by producing hybrid features from the support examples of each class. The refined prototypes help to classify the query images better. Our method can replace the evaluation phase of any few-shot learning method that uses a nearest neighbor prototype-based evaluation procedure to make them robust. We evaluate our method on standard mini-ImageNet and tiered-ImageNet datasets. We perform experiments with various label corruption rates in the support examples of the few-shot classes. We obtain significant improvement over widely used few-shot learning methods that suffer significant performance degeneration in the presence of label noise. We finally provide extensive ablation experiments to validate our method.