GraFIQs: Face Image Quality Assessment Using Gradient Magnitudes
This addresses the need for efficient face image quality assessment in biometric systems, offering an incremental improvement by eliminating labeling and training requirements.
The paper tackled the problem of assessing face image quality for automated recognition systems by proposing a training-free method based on gradient magnitudes of pretrained model weights, achieving competitive performance to state-of-the-art approaches without requiring quality labels or specialized training.
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.