Efficient-PrototypicalNet with self knowledge distillation for few-shot learning

Computer Science

• Knowledge Distillation 100%
• Few-Shot Learning 100%
• Image Classification 16%
• Performance Improvement 16%
• Classification Models 16%
• Learning Framework 16%
• Classification Task 16%
• Art Performance 16%
• Transfer Learning 16%
• Generalizability 16%
• Computational Cost 16%

Keyphrases

• Self-distillation 100%
• Training Difficulty 16%
• Applied Knowledge 16%
• Omniglot 16%