A Deep Mixed-Image Augmentation Strategy for Few-Shot Image Classification

Wang, Rui; Liu, Xiaomin

doi:10.3390/computers15090578

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

A Deep Mixed-Image Augmentation Strategy for Few-Shot Image Classification

by

Rui Wang

and

Xiaomin Liu

^*

Information and Electronic Technology Institute, Jiamusi University, Jiamusi 154007, China

^*

Author to whom correspondence should be addressed.

Computers 2026, 15(9), 578; https://doi.org/10.3390/computers15090578 (registering DOI)

Submission received: 31 July 2026 / Revised: 31 August 2026 / Accepted: 31 August 2026 / Published: 3 September 2026

Download Versions Notes

Abstract

Few-shot image classification suffers from severe data scarcity and unstable generalization. Existing data augmentation strategies still have three major limitations: pixel-level fusion strategies are incompatible with the support–query structure of episodic learning, category selection for cropping-based augmentation is overly simplistic, and most approaches rely on a single augmentation method, limiting robustness. To address these issues, this study proposes a deep mixed data augmentation framework that jointly enhances both the support set and the query set. The method first performs global pixel-level fusion to construct fused support and query sets. A Hopfield network then turns fused-support similarities into a pairing matrix

H

, which assigns a different-class gallery partner for query-side cropping–mixing. Finally, cropping–mixing produces an enhanced query set for model training. The framework is validated using ResNet18+BDC as the backbone. Experimental results on MiniImageNet demonstrate that the proposed method is competitive in few-shot classification, attaining a five-seed test mean of

73.25

%/

81.88

% under 5-way 1-shot and 5-shot. A single complementary run on FC100 attains

66.63

%/

77.80

% and is not a same-backbone ranking against heterogeneous published protocols.

Keywords: few-shot classification; data augmentation; global pixel-level fusion; Hopfield network; episodic learning

Share and Cite

MDPI and ACS Style

Wang, R.; Liu, X. A Deep Mixed-Image Augmentation Strategy for Few-Shot Image Classification. Computers 2026, 15, 578. https://doi.org/10.3390/computers15090578

AMA Style

Wang R, Liu X. A Deep Mixed-Image Augmentation Strategy for Few-Shot Image Classification. Computers. 2026; 15(9):578. https://doi.org/10.3390/computers15090578

Chicago/Turabian Style

Wang, Rui, and Xiaomin Liu. 2026. "A Deep Mixed-Image Augmentation Strategy for Few-Shot Image Classification" Computers 15, no. 9: 578. https://doi.org/10.3390/computers15090578

APA Style

Wang, R., & Liu, X. (2026). A Deep Mixed-Image Augmentation Strategy for Few-Shot Image Classification. Computers, 15(9), 578. https://doi.org/10.3390/computers15090578

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.

Article Menu

A Deep Mixed-Image Augmentation Strategy for Few-Shot Image Classification

Abstract

Share and Cite

Article Metrics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI