Calibrated Focal Loss for Semantic Labeling of High-Resolution Remote Sensing Images
Currently, the most advanced high-resolution remote sensing image (HRRSI) semantic labeling methods rely on deep neural networks. However, HRRSIs naturally have a serious class imbalance problem, which is not yet well solved by the current method. The cross-entropy loss is often used to guide the tr...
| Main Authors: | , , , , |
|---|---|
| 格式: | Article |
| 語言: | English |
| 出版: |
IEEE
2022-01-01
|
| 叢編: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| 主題: | |
| 在線閱讀: | https://ieeexplore.ieee.org/document/9854049/ |