轻量级人脸图像质量评估模型，准确率高且适合实际部署。
A Lightweight Ensemble-Based Face Image Quality Assessment Method with Correlation-Aware Loss
- 用两个小型网络集成，通过平均融合预测结果。
- 在VQualA数据集上达到SRCC 0.9829，PLCC 0.9894。
- 引入相关性感知损失，更贴近人眼判断。
人脸图像质量评估（FIQA）在非受控真实场景的面部识别与验证系统中至关重要。尽管已有多种方法提出，通用无参考图像质量评估技术往往无法捕捉人脸特有的退化特征。同时，当前最先进的FIQA模型计算开销大，限制了实际应用。本文提出一种轻量高效的人脸图像质量评估方法，专为野外场景中的人脸图像感知评价设计。方法整合两个紧凑型卷积神经网络（MobileNetV3-Small 和 ShuffleNetV2），采用预测层面的简单平均融合策略。为增强与人类感知判断的一致性，引入相关性感知损失（MSECorrLoss），结合均方误差（MSE）与皮尔逊相关系数正则项。实验表明，该模型在VQualA FIQA基准上取得0.9829的斯皮尔曼等级相关系数（SRCC）和0.9894的皮尔逊线性相关系数（PLCC），在保持高精度的同时满足竞赛效率约束。
原文摘要 · Abstract (English)
Face image quality assessment (FIQA) plays a critical role in face recognition and verification systems, especially in uncontrolled, real-world environments. Although several methods have been proposed, general-purpose no-reference image quality assessment techniques often fail to capture face-specific degradations. Meanwhile, state-of-the-art FIQA models tend to be computationally intensive, limiting their practical applicability. We propose a lightweight and efficient method for FIQA, designed for the perceptual evaluation of face images in the wild. Our approach integrates an ensemble of two compact convolutional neural networks, MobileNetV3-Small and ShuffleNetV2, with prediction-level fusion via simple averaging. To enhance alignment with human perceptual judgments, we employ a correlation-aware loss (MSECorrLoss), combining mean squared error (MSE) with a Pearson correlation regularizer. Our method achieves a strong balance between accuracy and computational cost, making it suitable for real-world deployment. Experiments on the VQualA FIQA benchmark demonstrate that our model achieves a Spearman rank correlation coefficient (SRCC) of 0.9829 and a Pearson linear correlation coefficient (PLCC) of 0.9894, remaining within competition efficiency constraints.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。