Continual learning via knowledge distillation achieves SOTA 74.28% accuracy on new compound facial expression classes and 100% in one-shot learning.
icarl: Incremental classifier and representation learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Complex Facial Expression Recognition Using Deep Knowledge Distillation of Basic Features
Continual learning via knowledge distillation achieves SOTA 74.28% accuracy on new compound facial expression classes and 100% in one-shot learning.