Quantum Few-Shot Image Classification

doi:10.1109/TCYB.2024.3476339

Quantum Few-Shot Image Classification

2025-01-01

0

PRE

AI

DOI：10.1109/TCYB.2024.3476339

Original

Original request for help

Save

Abstract

En 中文

Few-shot learning algorithms frequently exhibit suboptimal performance due to the limited availability of labeled data. This article presents a novel quantum few-shot image classification methodology aimed at enhancing the efficacy of few-shot learning algorithms at both the data and parameter levels. Initially, a quantum augmentation image representation technique is introduced, leveraging the local phase of quantum states to support few-shot learning algorithms at the data level. This approach enriches classical data while maintaining its intrinsic physical properties. Subsequently, a parameterized quantum circuit is employed to construct the classification model. This circuit, characterized by a reduced number of trainable parameters, shows increased resilience to overfitting, thereby offering a significant advantage at the parameter level for few-shot learning algorithms. The proposed approach is validated using three datasets, with experimental results indicating that it outperforms classical methods in few-shot learning scenarios while requiring fewer computational resources.

Keywords:

Data augmentation

few-shot learning

quantum machine learning (QML)

self-supervised learning

Data augmentation

few-shot learning

quantum machine learning (QML)

self-supervised learning

Quantum Few-Shot Image Classification

Abstract

Journal

Organization