Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments
arXiv:1708.08197
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.
arXiv comment10 pages, 9 figures
References in corpus (5)
Cited by in corpus (63)
- Deep Face Recognition: A Survey
- SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition
- SwinFace: A Multi-task Transformer for Face Recognition, Expression Recognition, Age Estimation and Attribute Estimation
- Deep Polynomial Neural Networks
- 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
- Cross-Quality LFW: A Database for Analyzing Cross-Resolution Image Face Recognition in Unconstrained Environments
- Lightweight Pixel Difference Networks for Efficient Visual Representation Learning
- Face Transformer for Recognition
- EasyQuant: Post-training Quantization via Scale Optimization
- ATFaceGAN: Single Face Image Restoration and Recognition from Atmospheric Turbulence
- MagFace: A Universal Representation for Face Recognition and Quality Assessment
- DuetFace: Collaborative Privacy-Preserving Face Recognition via Channel Splitting in the Frequency Domain
- Partial FC: Training 10 Million Identities on a Single Machine
- CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition
- SphereFace2: Binary Classification is All You Need for Deep Face Recognition
- Face Image Quality Assessment: A Literature Survey
- WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition
- Extended T: Learning with Mixed Closed-set and Open-set Noisy Labels
- Masked Face Recognition Challenge: The WebFace260M Track Report
- LOTR: Face Landmark Localization Using Localization Transformer
- Explainable Model-Agnostic Similarity and Confidence in Face Verification
- Cross-Resolution Face Recognition via Prior-Aided Face Hallucination and Residual Knowledge Distillation
- xCos: An Explainable Cosine Metric for Face Verification Task
- Membership Leakage in Label-Only Exposures
- FaceX-Zoo: A PyTorch Toolbox for Face Recognition
- Octuplet Loss: Make Face Recognition Robust to Image Resolution
- Mis-classified Vector Guided Softmax Loss for Face Recognition
- NPCFace: Negative-Positive Collaborative Training for Large-scale 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
- Federated Face Recognition
- Domain Balancing: Face Recognition on Long-Tailed Domains
- LiBRe: A Practical Bayesian Approach to Adversarial Detection
- 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
- NPT-Loss: A Metric Loss with Implicit Mining for Face Recognition
- Prototype Memory for Large-scale Face Representation Learning
- Quality-Diversity Generative Sampling for Learning with Synthetic Data
- ID-Booth: Identity-consistent Face Generation with Diffusion Models
- MultiFace: A Generic Training Mechanism for Boosting Face Recognition Performance
- SeesawFaceNets: sparse and robust face verification model for mobile platform
- PAM: Pose Attention Module for Pose-Invariant Face Recognition
- GB-CosFace: Rethinking Softmax-based Face Recognition from the Perspective of Open Set Classification
- Face Recognition in Unconstrained Conditions: A Systematic Review
- An Efficient Training Approach for Very Large Scale Face Recognition
- Sub-pixel face landmarks using heatmaps and a bag of tricks
- More Information Supervised Probabilistic Deep Face Embedding Learning
- Dynamic Class Queue for Large Scale Face Recognition In the Wild
- Inter-class Discrepancy Alignment for Face Recognition
- EQFace: A Simple Explicit Quality Network for Face Recognition
- Uncovering the Connections Between Adversarial Transferability and Knowledge Transferability
- Multi-Agent Semi-Siamese Training for Long-tail and Shallow Face Learning
- Semi-Siamese Training for Shallow Face Learning
- Set-Based Face Recognition Beyond Disentanglement: Burstiness Suppression With Variance Vocabulary
- Neutral Face Game Character Auto-Creation via PokerFace-GAN
- Multi-Head Encoding for Extreme Label Classification
- Fast and Robust Face-to-Parameter Translation for Game Character Auto-Creation
- Boosting Semi-Supervised Face Recognition with Noise Robustness
- Quadric Hypersurface Intersection for Manifold Learning in Feature Space
- Structure-Regularized Attention for Deformable Object Representation
- MLFW: A Database for Face Recognition on Masked Faces
- AsymmNet: Towards ultralight convolution neural networks using asymmetrical bottlenecks