Hierarchical Prototypes Polynomial Softmax Loss Function for Visual Classification

Hierarchical Prototypes Polynomial Softmax Loss Function for Visual Classification

A well-designed loss function can effectively improve the characterization ability of network features without increasing the amount of calculation in the model inference stage, and has become the focus of attention in recent research. Given that the existing lightweight network adds a loss to the l...

Full description

Bibliographic Details
Main Authors: Chengcheng Xiao, Xiaowen Liu, Chi Sun, Zhongyu Liu, Enjie Ding
Format: Article
Language:English
Published: MDPI AG 2022-10-01
Series:Applied Sciences
Subjects:
deep learning
light-weight convolutional neural networks
loss function
visual classification
Online Access:https://www.mdpi.com/2076-3417/12/20/10336

Internet

https://www.mdpi.com/2076-3417/12/20/10336

Similar Items