Few-shot Image Classification based on Gradual Machine Learning

TL;DR

This paper introduces a gradual machine learning approach for few-shot image classification that iteratively labels images based on difficulty, leveraging feature representations and factor graphs, achieving improved accuracy and robustness over deep learning methods.

Contribution

The paper presents a novel GML-based method for few-shot classification that outperforms state-of-the-art deep learning models in accuracy and robustness, especially with increasing query set size.

Findings

Improves accuracy by 1-5% over SOTA methods.

More robust than deep models as query set size increases.

Performance consistently improves with more data.

Abstract

Few-shot image classification aims to accurately classify unlabeled images using only a few labeled samples. The state-of-the-art solutions are built by deep learning, which focuses on designing increasingly complex deep backbones. Unfortunately, the task remains very challenging due to the difficulty of transferring the knowledge learned in training classes to new ones. In this paper, we propose a novel approach based on the non-i.i.d paradigm of gradual machine learning (GML). It begins with only a few labeled observations, and then gradually labels target images in the increasing order of hardness by iterative factor inference in a factor graph. Specifically, our proposed solution extracts indicative feature representations by deep backbones, and then constructs both unary and binary factors based on the extracted features to facilitate gradual learning. The unary factors are constructed based on class center distance in an embedding space, while the binary factors are constructed based on k-nearest neighborhood. We have empirically validated the performance of the proposed approach on benchmark datasets by a comparative study. Our extensive experiments demonstrate that the proposed approach can improve the SOTA performance by 1-5% in terms of accuracy. More notably, it is more robust than the existing deep models in that its performance can consistently improve as the size of query set increases while the performance of deep models remains essentially flat or even becomes worse.