Uncertainty-Aware Few-Shot Image Classification

TL;DR

This paper introduces an uncertainty-aware framework for few-shot image classification that models the uncertainty in query-support similarities, leading to improved optimization and state-of-the-art results.

Contribution

It proposes a novel method that converts similarities into probabilistic representations and uses a graph-based model to estimate uncertainty, enhancing few-shot learning performance.

Findings

Significant performance improvements over baseline methods.

Achieves state-of-the-art results on benchmark datasets.

Effectively models uncertainty to optimize few-shot classification.

Abstract

Few-shot image classification learns to recognize new categories from limited labelled data. Metric learning based approaches have been widely investigated, where a query sample is classified by finding the nearest prototype from the support set based on their feature similarities. A neural network has different uncertainties on its calculated similarities of different pairs. Understanding and modeling the uncertainty on the similarity could promote the exploitation of limited samples in few-shot optimization. In this work, we propose Uncertainty-Aware Few-Shot framework for image classification by modeling uncertainty of the similarities of query-support pairs and performing uncertainty-aware optimization. Particularly, we exploit such uncertainty by converting observed similarities to probabilistic representations and incorporate them to the loss for more effective optimization. In order to jointly consider the similarities between a query and the prototypes in a support set, a graph-based model is utilized to estimate the uncertainty of the pairs. Extensive experiments show our proposed method brings significant improvements on top of a strong baseline and achieves the state-of-the-art performance.