CLFace removes the classification layer from continual face recognition and uses multiscale, geometry, and contrastive distillation to update a student model without labels or exemplars, reporting gains on unseen-identity benchmarks.
Learning without mem- orizing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CLFace: A Scalable and Resource-Efficient Continual Learning Framework for Lifelong Face Recognition
CLFace removes the classification layer from continual face recognition and uses multiscale, geometry, and contrastive distillation to update a student model without labels or exemplars, reporting gains on unseen-identity benchmarks.