Pith. sign in

Besides, we use default training configurations for PartialFace implementation (Mi et al., 2023)9, 27 random sub channels are selecting for training

Optimizer SGD Loss Function ArcFace Epoch 24 Batch Size 128 For the detailed setting of ArcFace loss, scale s = 64 , weight w = 1 · 2023

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

fields

cs.CV 1

years

2024 1

verdicts

CONDITIONAL 1

representative citing papers

KAN See Your Face

cs.CV · 2024-11-27 · conditional · novelty 5.0

A KAN-based mapping network can translate embeddings from privacy-preserving face recognition systems into the input space of a face diffusion model, enabling face reconstruction attacks with high attack success rates.

citing papers explorer

Showing 1 of 1 citing paper.

  • KAN See Your Face cs.CV · 2024-11-27 · conditional · none · ref 2016

    A KAN-based mapping network can translate embeddings from privacy-preserving face recognition systems into the input space of a face diffusion model, enabling face reconstruction attacks with high attack success rates.