Facial attribute editing using generative models can impair automated face
recognition. This degradation persists even with recent identity-preserving
models such as InstantID. To mitigate this issue, we propose two techniques
that perform local and global attribute editing. Local editing operates on the
finer details via a regularization-free method based on ControlNet conditioned
on depth maps and auxiliary semantic segmentation masks. Global editing
operates on coarser details via a regularization-based method guided by custom
loss and regularization set. In this work, we empirically ablate twenty-six
facial semantic, demographic and expression-based attributes altered 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, a
vision-language framework for attribute prediction to validate our editing
techniques. Our methods outperform SoTA (BLIP, InstantID) at facial editing
while retaining identity.

通过使用基于深度图和辅助语义分割掩模的 ControlNet 的无正则方法进行精细的局部属性编辑和基于自定义损失和正则化设置的基于正则方法进行粗糙的全局属性编辑，本研究对利用最新的生成模型改变的二十六种面部语义、人口统计和表情属性进行了实证消融，并在 CelebA、CelebAMaskHQ 和 LFW 数据集上使用 ArcFace 和 AdaFace 匹配器进行了评估，最终使用 LLaVA 验证了我们的编辑技术，方法在保留身份的情况下，在面部编辑方面优于现有技术（BLIP、InstantID）。

缓解属性编辑对人脸识别的影响

Mitigating the Impact of Attribute Editing on Face Recognition

Automated face recognition is a widely adopted machine learning technology
for contactless identification of people in various processes such as automated
border control, secure login to electronic devices, community surveillance,
tracking school attendance, workplace clock in and clock out. Using face masks
have become crucial in our daily life with the recent world-wide COVID-19
pandemic. The use of face masks causes the performance of conventional face
recognition technologies to degrade considerably. The effect of mask-wearing in
face recognition is yet an understudied issue. In this paper, we address this
issue by evaluating the performance of a number of face recognition models
which are tested by identifying masked and unmasked face images. We use six
conventional machine learning algorithms, which are SVC, KNN, LDA, DT, LR and
NB, to find out the ones which perform best, besides the ones which poorly
perform, in the presence of masked face images. Local Binary Pattern (LBP) is
utilized as the feature extraction operator. We generated and used synthesized
masked face images. We prepared unmasked, masked, and half-masked training
datasets and evaluated the face recognition performance against both masked and
unmasked images to present a broad view of this crucial problem. We believe
that our study is unique in elaborating the mask-aware facial recognition with
almost all possible scenarios including half_masked-to-masked and
half_masked-to-unmasked besides evaluating a larger number of conventional
machine learning algorithms compared the other studies in the literature.

本文介绍了一项关于带口罩可识别面部的研究，通过使用 6 种机器学习算法并生成遮面脸部图像，我们评估了这些算法在带口罩和不带口罩的情况下的识别表现。