Mitigating the Impact of Attribute Editing on Face Recognition

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Banerjee, Sudipta, Mullangi, Sai Pranaswi, Wagle, Shruti, Hegde, Chinmay, Memon, Nasir
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909164817612800
author Banerjee, Sudipta
Mullangi, Sai Pranaswi
Wagle, Shruti
Hegde, Chinmay
Memon, Nasir
author_facet Banerjee, Sudipta
Mullangi, Sai Pranaswi
Wagle, Shruti
Hegde, Chinmay
Memon, Nasir
contents Through a large-scale study over diverse face images, we show that facial attribute editing using modern generative AI models can severely degrade automated face recognition systems. This degradation persists even with identity-preserving generative models. To mitigate this issue, we propose two novel techniques for local and global attribute editing. We empirically ablate twenty-six facial semantic, demographic and expression-based attributes that have been edited using state-of-the-art generative models, and evaluate them using ArcFace and AdaFace matchers on CelebA, CelebAMaskHQ and LFW datasets. Finally, we use LLaVA, an emerging visual question-answering framework for attribute prediction to validate our editing techniques. Our methods outperform the current state-of-the-art at facial editing (BLIP, InstantID) while improving identity retention by a significant extent.
format Preprint
id arxiv_https___arxiv_org_abs_2403_08092
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Mitigating the Impact of Attribute Editing on Face Recognition
Banerjee, Sudipta
Mullangi, Sai Pranaswi
Wagle, Shruti
Hegde, Chinmay
Memon, Nasir
Computer Vision and Pattern Recognition
Through a large-scale study over diverse face images, we show that facial attribute editing using modern generative AI models can severely degrade automated face recognition systems. This degradation persists even with identity-preserving generative models. To mitigate this issue, we propose two novel techniques for local and global attribute editing. We empirically ablate twenty-six facial semantic, demographic and expression-based attributes that have been edited using state-of-the-art generative models, and evaluate them using ArcFace and AdaFace matchers on CelebA, CelebAMaskHQ and LFW datasets. Finally, we use LLaVA, an emerging visual question-answering framework for attribute prediction to validate our editing techniques. Our methods outperform the current state-of-the-art at facial editing (BLIP, InstantID) while improving identity retention by a significant extent.
title Mitigating the Impact of Attribute Editing on Face Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.08092