A Systematic Review on Long-Tailed Learning

Autor: Zhang, Chongsheng, Almpanidis, George, Fan, Gaojuan, Deng, Binquan, Zhang, Yanbo, Liu, Ji, Kamel, Aouaidjia, Soda, Paolo, Gama, João

Long-tailed data is a special type of multi-class imbalanced data with a very large amount of minority/tail classes that have a very significant combined influence. Long-tailed learning aims to build high-performance models on datasets with long-tail

Externí odkaz: http://arxiv.org/abs/2408.00483

Open-set long-tailed recognition via orthogonal prototype learning and false rejection correction.

Autor: Deng B; School of Computer and information Engineering, Henan University, 475004, Kaifeng, China. Electronic address: bqdeng@henu.edu.cn., Kamel A; School of Computer and information Engineering, Henan University, 475004, Kaifeng, China. Electronic address: kameldz40@gmail.com., Zhang C; School of Computer and information Engineering, Henan University, 475004, Kaifeng, China. Electronic address: cszhang@ieee.org.

Publikováno v: Neural networks : the official journal of the International Neural Network Society [Neural Netw] 2024 Oct 11; Vol. 181, pp. 106789. Date of Electronic Publication: 2024 Oct 11.