SAR Target Incremental Recognition Based on Hybrid Loss Function and Class-Bias Correction

SAR Target Incremental Recognition Based on Hybrid Loss Function and Class-Bias Correction

The Synthetic Aperture Radar (SAR) target recognition model usually needs to be retrained with all the samples when there are new-coming samples of new targets. Incremental learning emerges to continuously obtain new knowledge from new data while preserving most previously learned knowledge, saving...

Full description

Bibliographic Details
Main Authors: Yongsheng Zhou, Shuo Zhang, Xiaokun Sun, Fei Ma, Fan Zhang
Format: Article
Language:English
Published: MDPI AG 2022-01-01
Series:Applied Sciences
Subjects:
incremental learning
SAR target recognition
knowledge distillation
old sample preservation
class imbalance
Online Access:https://www.mdpi.com/2076-3417/12/3/1279

Internet

https://www.mdpi.com/2076-3417/12/3/1279

Similar Items