Formalizes continual segmentation under coupled class-domain-label shifts and introduces gradient-adaptive stabilization plus prototype consistency for semi-supervised learning in heterogeneous dense prediction.
Face-CPFNet: Leveraging Disentangled Representations for Dual-Level Soft-Biometric Privacy- Enhancement
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
VLEED uses variational latent entropy estimation to separate categorical attributes from identity in face embeddings, achieving wider privacy-utility tradeoffs and bias reduction than prior methods on IJB-C, RFW, and VGGFace2.
citing papers explorer
-
Continual Segmentation under Joint Nonstationarity
Formalizes continual segmentation under coupled class-domain-label shifts and introduces gradient-adaptive stabilization plus prototype consistency for semi-supervised learning in heterogeneous dense prediction.
-
Variational Latent Entropy Estimation Disentanglement: Controlled Attribute Leakage for Face Recognition
VLEED uses variational latent entropy estimation to separate categorical attributes from identity in face embeddings, achieving wider privacy-utility tradeoffs and bias reduction than prior methods on IJB-C, RFW, and VGGFace2.