RNNP: A Robust Few-Shot Learning Approach
This paper tackles the practical problem of label noise in few-shot learning for practitioners who rely on potentially noisy crowd-sourced labels, offering an incremental improvement to existing prototype-based methods.
This paper addresses the problem of label noise in few-shot learning, where existing methods assume perfectly labeled examples. The proposed RNNP method generates robust prototypes from noisy support examples, leading to significant performance improvements over existing few-shot learning methods on mini-ImageNet and tiered-ImageNet datasets when label corruption is present.
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.