LAUSR

Rectified Softmax Loss With All-Sided Cost Sensitivity for Age Estimation

Sign Up to like & get
recommendations!
1 Published in 2020 at "IEEE Access"

DOI: 10.1109/access.2020.2964281

Abstract: In Convolutional Neural Network (ConvNet) based age estimation algorithms, softmax loss is usually chosen as the loss function directly, and the problems of Cost Sensitivity (CS), such as class imbalance and misclassification cost difference between… read more here.

Keywords: rectified softmax; loss; age estimation; softmax loss ... See more keywords