Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments

Abstract

Labeled Faces in the Wild (LFW) database has been widely utilized as the benchmark of unconstrained face verification and due to big data driven machine learning methods, the performance on the database approaches nearly 100%. However, we argue that this accuracy may be too optimistic because of some limiting factors. Besides different poses, illuminations, occlusions and expressions, cross-age face is another challenge in face recognition. Different ages of the same person result in large intra-class variations and aging process is unavoidable in real world face verification. However, LFW does not pay much attention on it. Thereby we construct a Cross-Age LFW (CALFW) which deliberately searches and selects 3,000 positive face pairs with age gaps to add aging process intra-class variance. Negative pairs with same gender and race are also selected to reduce the influence of attribute difference between positive/negative pairs and achieve face verification instead of attributes classification. We evaluate several metric learning and deep learning methods on the new database. Compared to the accuracy on LFW, the accuracy drops about 10%-17% on CALFW.

10 pages, 9 figures

References in corpus (3)

• Learning Face Representation from Scratch
• DeepID3: Face Recognition with Very Deep Neural Networks
• Noisy Softmax: Improving the Generalization Ability of DCNN via Postponing the Early Softmax Saturation

Cited by in corpus (29)

• SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition
• SwinFace: A Multi-task Transformer for Face Recognition, Expression Recognition, Age Estimation and Attribute Estimation
• When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework and A New Benchmark
• von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification
• Lightweight Pixel Difference Networks for Efficient Visual Representation Learning
• Face Transformer for Recognition
• EasyQuant: Post-training Quantization via Scale Optimization
• DuetFace: Collaborative Privacy-Preserving Face Recognition via Channel Splitting in the Frequency Domain
• Masked Face Recognition Challenge: The WebFace260M Track Report
• Extended T: Learning with Mixed Closed-set and Open-set Noisy Labels
• WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition
• Cross-Resolution Face Recognition via Prior-Aided Face Hallucination and Residual Knowledge Distillation
• Mis-classified Vector Guided Softmax Loss for Face Recognition
• CATFace: Cross-Attribute-Guided Transformer with Self-Attention Distillation for Low-Quality Face Recognition
• GroupFace: Learning Latent Groups and Constructing Group-based Representations for Face Recognition
• NPT-Loss: A Metric Loss with Implicit Mining for Face Recognition
• Joint Feature Distribution Alignment Learning for NIR-VIS and VIS-VIS Face Recognition
• BroadFace: Looking at Tens of Thousands of People at Once for Face Recognition
• Inter-class Discrepancy Alignment for Face Recognition
• Sub-pixel face landmarks using heatmaps and a bag of tricks
• Dynamic Class Queue for Large Scale Face Recognition In the Wild
• More Information Supervised Probabilistic Deep Face Embedding Learning
• Set-Based Face Recognition Beyond Disentanglement: Burstiness Suppression With Variance Vocabulary
• Fast and Robust Face-to-Parameter Translation for Game Character Auto-Creation
• Semi-Siamese Training for Shallow Face Learning
• Neutral Face Game Character Auto-Creation via PokerFace-GAN
• MLFW: A Database for Face Recognition on Masked Faces
• AsymmNet: Towards ultralight convolution neural networks using asymmetrical bottlenecks
• Structure-Regularized Attention for Deformable Object Representation