无需训练，单次前向传播即可评估人脸图像质量
ViTNT-FIQA: Training-Free Face Image Quality Assessment with Vision Transformers
- 利用ViT中间层块的特征稳定性判断图像质量
- 在8个基准数据集上达到顶尖性能，计算高效
- 适合快速部署于任意预训练ViT模型的人脸识别系统
人脸图像质量评估（FIQA）对可靠的人脸识别系统至关重要。现有方法主要依赖最终层表示，而无训练方法通常需要多次前向传播或反向传播。我们提出ViTNT-FIQA，一种无需训练的方法，通过测量视觉变换器（ViT）中间块中局部图像块嵌入的演化稳定性来评估质量。实验证明，高质量人脸图像在各块间呈现稳定特征优化轨迹，劣质图像则表现出不规则变化。该方法计算连续块间归一化嵌入的欧氏距离，并聚合为图像级质量分数。我们在一个带有可控退化级别的合成标注数据集上验证了这一相关性。与现有无训练方法不同，ViTNT-FIQA仅需一次前向传播，无需反向传播或结构修改。在八个基准数据集（LFW、AgeDB-30、CFP-FP、CALFW、Adience、CPLFW、XQLFW、IJB-C）上的大量实验表明，其性能媲美当前最优方法，同时保持计算效率和对任意预训练ViT人脸识别模型的即插即用性。
原文摘要 · Abstract (English)
Face Image Quality Assessment (FIQA) is essential for reliable face recognition systems. Current approaches primarily exploit only final-layer representations, while training-free methods require multiple forward passes or backpropagation. We propose ViTNT-FIQA, a training-free approach that measures the stability of patch embedding evolution across intermediate Vision Transformer (ViT) blocks. We demonstrate that high-quality face images exhibit stable feature refinement trajectories across blocks, while degraded images show erratic transformations. Our method computes Euclidean distances between L2-normalized patch embeddings from consecutive transformer blocks and aggregates them into image-level quality scores. We empirically validate this correlation on a quality-labeled synthetic dataset with controlled degradation levels. Unlike existing training-free approaches, ViTNT-FIQA requires only a single forward pass without backpropagation or architectural modifications. Through extensive evaluation on eight benchmarks (LFW, AgeDB-30, CFP-FP, CALFW, Adience, CPLFW, XQLFW, IJB-C), we show that ViTNT-FIQA achieves competitive performance with state-of-the-art methods while maintaining computational efficiency and immediate applicability to any pre-trained ViT-based face recognition model.
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。