A Class Imbalance Loss for Imbalanced Object Recognition

The class imbalance problem exists widely in vision data. In these imbalanced datasets, the majority classes dominate the loss and influence the gradient. Hence, these datasets have a significantly negative impact on the performance of many state-of-the-art methods. In this article, we propose a cla...

Full description

Bibliographic Details
Main Authors: Linbin Zhang, Caiguang Zhang, Sinong Quan, Huaxin Xiao, Gangyao Kuang, Li Liu
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/9103243/