自动化学报2025，Vol.51Issue(5)：985-1020,36.DOI:10.16383/j.aas.c240077
深度长尾学习研究综述
Survey on Deep Long-tailed Learning
韩佳艺 1刘建伟 1陈德华 2徐璟东 1代琪 1夏鹏飞2
作者信息
- 1. 中国石油大学(北京)人工智能学院自动化系 北京 102249
- 2. 东华大学计算机科学与技术学院 上海 201620
- 折叠
摘要
Abstract
Deep learning is a science that depends on data.Traditional deep learning methods unrealistically as-sume that the training models are on balanced datasets.In real-world large-scale datasets,a long-tailed distribution often occurs,with a few head classes having many samples dominating model training,while many tail classes have too few samples to be adequately learned.In recent years,the long-tailed learning has set off a research upsurge in academic circles.In this paper,we comb and analyze the literature published in high-level conferences or journals to provide a comprehensive survey of long-tailed learning.Specifically,we categorize long-tailed learning algorithms in the field of image recognition into three main types according to the design process of deep learning models:Optim-izing the sample space by enriching the quantity and semantic information of samples,optimizing the model by fo-cusing on the four fundamental components of feature extractor,classifier,logits and loss function,and auxiliary task learning,which involves introducing auxiliary tasks to aid model training and jointly optimizing long-tailed learning models across multiple spaces.Additionally,a comprehensive comparative analysis of the strengths and weaknesses of each category is conducted based on the proposed classification method.We further extend the concept of narrow long-tail learning based on the number of samples to multi-scale generalized long-tailed learning.In addition,we briefly review long-tailed learning algorithms in other data forms,such as text data and voice data.Finally,we discuss the current challenges faced by long-tailed learning,such as poor interpretability and low data quality,and look forward to the future development directions,such as multimodal long-tailed learning and semi-su-pervised long-tailed learning.关键词
深度长尾学习/长尾分布/不平衡学习/深度学习Key words
Deep long-tailed learning/long-tailed distribution/imbalanced learning/deep learning引用本文复制引用
韩佳艺,刘建伟,陈德华,徐璟东,代琪,夏鹏飞..深度长尾学习研究综述[J].自动化学报,2025,51(5):985-1020,36.
