摘要
深度学习方法在图像分类、目标检测、特征识别和故障诊断等领域取得了卓越成果.然而,在实际应用中诸多限制使得通常无法获取大量的样本数据.因此,近几年在小样本情况下进行学习的算法成为学术研究热点.本篇综述的目标是概述主流的小样本学习方法及其在典型应用场景中的效果.在具体的算法方面,总结了包括度量模型、记忆模型、参数更新模型和样本扩充模型等不同方法的优势和缺点.阐述了现有小样本学习方法在图像分类、目标检测、语义分割和故障诊断4个典型领域的应用情况.对小样本学习不同方法的局限性进行了讨论,并且从数据的低依赖性,算法的高效化和模型的鲁棒性3个角度分析了未来的小样本学习研究的趋势.
Deep learning methods have achieved great success in tasks like image classification,object detection and fault diagnosis.However,practical limitations often prevent gathering large amounts of data.Hence,there is a recent focus on algorithms for learning with small samples.This review aims to explain popular small sample learning methods and how they perform in real-world applications.The review covers different approaches like metric models,memory models,parameter updating models and sample augmentation models,discussing their pros and cons.It also explores how these methods are applied in tasks like image classification,object detection,semantic segmentation and fault diagnosis.Lastly,it discusses the limitations of small sample learning methods and predicts future research trends focusing on less data dependency,more efficient algorithms and robust models.
作者
王圣杰
王铎
梁秋金
金渝皓
刘磊
张涛
WANG Shengjie;WANG Duo;LIANG Qiujin;JIN Yuhao;LIU Lei;ZHANG Tao(Department of Automation,Tsinghua University,Beijing 100084,China;Beijing Institute of Control Engineering,Beijing 100094,China)
出处
《空间控制技术与应用》
CSCD
北大核心
2023年第5期1-10,共10页
Aerospace Control and Application
基金
国家自然科学基金资助项目(U21B6002)。
关键词
深度学习
小样本学习
度量学习
图像分类
目标检测
deep learning
few-shot learning
metric learning
image classification
object detection
