Search Results for author:
Found 5 papers, 3 papers with code
HFORD: High-Fidelity and Occlusion-Robust De-identification for Face Privacy Protection
To disentangle the latent codes in the GAN inversion space, we introduce an Identity Disentanglement Module (IDM).
DED: Diagnostic Evidence Distillation for acne severity grading on face images
In this study, we propose an acne diagnosis method, Diagnostic Evidence Distillation (DED), that suitably adapts the characteristics of acne diagnosis and can be applied to diagnose under different acne criteria.
Ranked #1 on
Acne Severity Grading
on ACNE04
(Accuracy metric)
Diff-Privacy: Diffusion-based Face Privacy Protection
In this paper, we unify the task of anonymization and visual identity information hiding and propose a novel face privacy protection method based on diffusion models, dubbed Diff-Privacy.
Acne Severity Grading on Face Images via Extraction and Guidance of Prior Knowledge
Acne Vulgaris seriously affects people’s daily life.
Ranked #2 on
Acne Severity Grading
on ACNE04
(Accuracy metric)
KIEGLFN: A unified acne grading framework on face images
Methods: A unified acne grading framework that can be generalized to apply referring to different grading criteria is developed.
Ranked #3 on
Acne Severity Grading
on ACNE04
(Accuracy metric)
