Feature Decoupled Knowledge Distillation via Spatial Pyramid Pooling

Decoupled Knowledge Distillation via Spatial Feature Blurring for Hyperspectral Image Classification

“…where α and β are hyperparameters that need to be manually set. In CIFAR-100 and ImageNet classification tasks, using the DKD strategy yields better results compared to using KD strategy based on intermediate layer features [50]- [52].…”