自适应融合局部与全局特征，提升低质量人脸图像识别准确率。
Local and Global Feature Attention Fusion Network for Face Recognition
- 根据特征质量动态分配局部与全局注意力，实现互补增强。
- 在4个基准数据集上平均性能最优，TinyFace和SCFace超越现有方法。
- 适合处理部分缺失或局部变形的低质量人脸图像识别任务。
低质量人脸图像因局部区域缺失或形变仍难识别。当图像以局部缺失为主时，局部相似性对识别更关键；当局部形变严重时，过度关注局部易导致误判，而全局特征更具鲁棒性。然而，现有方法普遍忽略不同因素引起的特征质量偏差。为此，我们提出基于特征质量的局部与全局特征注意力融合（LGAF）网络，根据特征质量自适应分配局部与全局注意力，通过信息互补获得更具区分性的高质量特征。此外，为有效获取多尺度细粒度信息并增强高维空间中特征可分性，引入多头多尺度局部特征提取（MHMS）模块。实验表明，LGAF在4个验证集（CFP-FP、CPLFW、AgeDB、CALFW）上达到最佳平均性能，且在TinyFace和SCFace上的表现优于当前最先进方法（SoTA）。
原文摘要 · Abstract (English)
Recognition of low-quality face images remains a challenge due to invisible or deformation in partial facial regions. For low-quality images dominated by missing partial facial regions, local region similarity contributes more to face recognition (FR). Conversely, in cases dominated by local face deformation, excessive attention to local regions may lead to misjudgments, while global features exhibit better robustness. However, most of the existing FR methods neglect the bias in feature quality of low-quality images introduced by different factors. To address this issue, we propose a Local and Global Feature Attention Fusion (LGAF) network based on feature quality. The network adaptively allocates attention between local and global features according to feature quality and obtains more discriminative and high-quality face features through local and global information complementarity. In addition, to effectively obtain fine-grained information at various scales and increase the separability of facial features in high-dimensional space, we introduce a Multi-Head Multi-Scale Local Feature Extraction (MHMS) module. Experimental results demonstrate that the LGAF achieves the best average performance on $4$ validation sets (CFP-FP, CPLFW, AgeDB, and CALFW), and the performance on TinyFace and SCFace outperforms the state-of-the-art methods (SoTA).
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。