RoNFA: Robust Neural Field-based Approach for Few-Shot Image Classification with Noisy Labels

TL;DR

RoNFA introduces a neural field-based method for few-shot image classification that maintains high accuracy even with noisy labels, outperforming existing approaches by adapting to label errors.

Contribution

The paper presents a novel neural field architecture with adaptive receptive fields for robust few-shot learning under label noise conditions.

Findings

Significantly outperforms state-of-the-art FSL methods on noisy datasets.

Achieves higher accuracy with noisy labels than some methods trained on clean data.

Demonstrates strong robustness against various types of label noise.

Abstract

In few-shot learning (FSL), the labeled samples are scarce. Thus, label errors can significantly reduce classification accuracy. Since label errors are inevitable in realistic learning tasks, improving the robustness of the model in the presence of label errors is critical. This paper proposes a new robust neural field-based image approach (RoNFA) for few-shot image classification with noisy labels. RoNFA consists of two neural fields for feature and category representation. They correspond to the feature space and category set. Each neuron in the field for category representation (FCR) has a receptive field (RF) on the field for feature representation (FFR) centered at the representative neuron for its category generated by soft clustering. In the prediction stage, the range of these receptive fields adapts according to the neuronal activation in FCR to ensure prediction accuracy. These learning strategies provide the proposed model with excellent few-shot learning capability and strong robustness against label noises. The experimental results on real-world FSL datasets with three different types of label noise demonstrate that the proposed method significantly outperforms state-of-the-art FSL methods. Its accuracy obtained in the presence of noisy labels even surpasses the results obtained by state-of-the-art FSL methods trained on clean support sets, indicating its strong robustness against noisy labels.