Face Image Quality Assessment (FIQA) estimates the utility of face images for
automated face recognition (FR) systems. We propose in this work a novel
approach to assess the quality of face images based on inspecting the required
changes in the pre-trained FR model weights to minimize differences between
testing samples and the distribution of the FR training dataset. To achieve
that, we propose quantifying the discrepancy in Batch Normalization statistics
(BNS), including mean and variance, between those recorded during FR training
and those obtained by processing testing samples through the pretrained FR
model. We then generate gradient magnitudes of pretrained FR weights by
backpropagating the BNS through the pretrained model. The cumulative absolute
sum of these gradient magnitudes serves as the FIQ for our approach. Through
comprehensive experimentation, we demonstrate the effectiveness of our
training-free and quality labeling-free approach, achieving competitive
performance to recent state-of-theart FIQA approaches without relying on
quality labeling, the need to train regression networks, specialized
architectures, or designing and optimizing specific loss functions.

基于对预训练模型权重的改变进行检查以评估人脸图像质量，采用批量归一化算法（BNS）的差异性作为评价指标，通过反向传播计算梯度大小来得出人脸图像的质量。通过全面实验，证明我们的方法不需要质量标签，也不需要训练回归网络或设计优化特定损失函数，仍能达到与最新技术水平相媲美的性能。

GraFIQs：使用梯度幅度进行人脸图像质量评估

GraFIQs: Face Image Quality Assessment Using Gradient Magnitudes

While the design of blind image quality assessment (IQA) algorithms has
improved significantly, the distribution shift between the training and testing
scenarios often leads to a poor performance of these methods at inference time.
This motivates the study of test time adaptation (TTA) techniques to improve
their performance at inference time. Existing auxiliary tasks and loss
functions used for TTA may not be relevant for quality-aware adaptation of the
pre-trained model. In this work, we introduce two novel quality-relevant
auxiliary tasks at the batch and sample levels to enable TTA for blind IQA. In
particular, we introduce a group contrastive loss at the batch level and a
relative rank loss at the sample level to make the model quality aware and
adapt to the target data. Our experiments reveal that even using a small batch
of images from the test distribution helps achieve significant improvement in
performance by updating the batch normalization statistics of the source model.

通过引入组对比损失和相对排序损失，使用测试分布中的少量图像批次可以显著提高模型性能，使盲目图像质量评估模型具备质量感知能力并适应目标数据。

盲目图像质量评估的测试时间适应

Test Time Adaptation for Blind Image Quality Assessment

While post-training quantization receives popularity mostly due to its
evasion in accessing the original complete training dataset, its poor
performance also stems from scarce images. To alleviate this limitation, in
this paper, we leverage the synthetic data introduced by zero-shot quantization
with calibration dataset and propose a fine-grained data distribution alignment
(FDDA) method to boost the performance of post-training quantization. The
method is based on two important properties of batch normalization statistics
(BNS) we observed in deep layers of the trained network, (i.e.), inter-class
separation and intra-class incohesion. To preserve this fine-grained
distribution information: 1) We calculate the per-class BNS of the calibration
dataset as the BNS centers of each class and propose a BNS-centralized loss to
force the synthetic data distributions of different classes to be close to
their own centers. 2) We add Gaussian noise into the centers to imitate the
incohesion and propose a BNS-distorted loss to force the synthetic data
distribution of the same class to be close to the distorted centers. By
utilizing these two fine-grained losses, our method manifests the
state-of-the-art performance on ImageNet, especially when both the first and
last layers are quantized to the low-bit. Code is at
https://github.com/zysxmu/FDDA.

本文利用零样本量化所介绍的合成数据及校准数据集，并提出了细粒度数据分布对齐（FDDA）方法，以提高后训练量化的性能。该方法基于深层网络中批量规范化统计量（BNS）观察到的两个重要属性，即类间分离和类内不凝聚，通过计算校准数据集的每一类 BNS 作为每一类的中心并提出中心化损失、在其中加入高斯噪声来模拟不凝聚和提出畸变损失。应用这两种细粒度损失函数，本方法在 ImageNet 上展现出最先进的性能，特别是在将第一层和最后一层量化为低位时。