Skip to content
Conference Open access

Evolution of Few-Shot Image Classification: A Survey from Metric Learning to Large Model Fine-Tuning

Sep 2026 · Exploring Science Academic Conference Series · 0 citations · 11 references

TL;DR

This survey comprehensively evaluates the underlying mechanisms, inherent strengths, and specific weaknesses of each FSIC methods into three categories: Metric Learning, Optimization/Meta-Learning, and Transfer Learning with Large Model Fine-Tuning.

Abstract

While deep learning has achieved remarkable success in image recognition, it relies heavily on massive amounts of labeled data. In real-world scenarios like medical imaging, collecting such large datasets is often expensive or impossible. To overcome this critical bottleneck, Few-Shot Image Classification (FSIC) has emerged as a vital domain, enabling models to learn new categories from extremely limited samples. Based on a comprehensive review of recent literature, this paper systematically divides mainstream FSIC methods into three categories: Metric Learning, Optimization/Meta-Learning, and Transfer Learning with Large Model Fine-Tuning. This survey comprehensively evaluates the underlying mechanisms, inherent strengths, and specific weaknesses of each category. Additionally, the paper provides a clear performance comparison to illustrate the evolutionary impact of these different approaches. Finally, the paper deeply discusses remaining technical challenges, specifically detailing issues like cross-domain generalization and computational dependence, and outlines promising future research directions, such as multimodal knowledge fusion, to further advance the field.

Read PDF

Similar papers

Open access Aug 2026

Few-shot image classification algorithm based on deep learning and feature fusion

Few-shot image classification remains difficult because a model must identify novel classes from only one or a few labeled examples while preserving discriminative local information. Metric-learning methods based on Earth Mover’s Distance (EMD) improve local correspondence by representing an image as a set of regional...

Huie Zhang, Mary Jane C. Samontet · 0 citations
Conference Sep 2026

A few-sample image classification method based on contrastive learning and data augmentation

Few-Shot Image Classification (FSL) aims to identify and classify new image categories using only a very small number of labeled samples. Addressing the shortcomings of existing meta-learning and metric learning methods, such as insufficient generalization of feature representations with very few samples, overfitting,...

Xua Li, Ru-Jun Wang · 0 citations
Sep 2026

EPPNet: Edge Prototype Purification with Auxiliary Supervision for Few-Shot Medical Image Segmentation.

An Auxiliary Supervision-guided Edge Prototype Purification Network (EPPNet) is proposed, which introduces a novel Prototype Purification Module (PPM) and selectively integrates high-confidence edge prototypes via a learnable adaptive threshold, aiming to substantially alleviate boundary feature contamination.

Wen-Jie Meng, Kai Liu, Minghui Wang · 0 citations
Sep 2026

A lightweight deep learning framework for cross-domain few-shot learning

A lightweight hierarchical representation learning framework is proposed with three key innovations that outperforms state-of-the-art methods across different settings and achieves a classification accuracy of 59.05% on EuroSAT 1-shot and 34.78% on ISIC 1-shot.

Lei-Lei Ding, Shu-Liang Zhao · 0 citations
Review Open access 2026

A Comprehensive Survey on Self-Supervised Learning on Computer Vision: Moving Beyond the Supervised Paradigm

This survey presents a seven-category taxonomy of self-supervised learning methods covering: 1) input reconstruction or restoration, 2) context prediction, 3) contrastive learning, 4) feature clustering, 5) self-distillation-based feature reconstruction, 6) redundancy reduction, and 7) masked image modeling.

Kriti Ohri, D. Sukheja, Purushottam Kumar et al. · 0 citations
Review Open access 2026

Few-Shot Hyperspectral Image Classification: A Review of Deep Architectures, Paradigms, and Benchmarks

A comprehensive review of recent advances in deep learning for few-shot HSI classification, systematically structured around core architectures, learning paradigms, and rigorous benchmarking to eliminate pervasive cross-study evaluation biases.

Qi-Yuan Wang, Shuo Zhang, Fei-Fei Yang et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.