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

By Tianyue Zheng, Weihong Deng, Jiani Hu. arXiv.org, 2017

525 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/3dfb822e16328e0f98a47209d7ecd242e4211f82

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Deep Face Recognition: A Survey (2018, unknown): “For example, CALFW [225], MORPH [128], CACD [24] and FG-NET [1] are commonly used datasets with different age range; CFP [138] only focuses on frontal and profile face, CPLFW [223] is extended from LFW with different poses.”
WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition (2021, background): “For example, CFP [49], AgeDB [37], CALFW [88] and CPLFW [63] evaluate the veriﬁcation accuracy under different intra-class variations ( e.g . pose and age).”
Membership Leakage in Label-Only Exposures (2020, background): “Machine learning (ML) has witnessed tremendous progress over the past decade and has been applied across a wide range of privacy-critical applications, such as face recognition [28, 61] and medical image analysis [9, 29, 51].”
AdaFace: Quality Adaptive Margin for Face Recognition (2022, background): “LFW [11] CFP-FP [27] CPLFW [43] AgeDB [25] CALFW [44] AVG IJB-B [37] IJB-C [22]”
SphereFace Revived: Unifying Hyperspherical Face Recognition (2021, unknown): “8M train LFW [77] 5,749 13,233 validation AgeDB-30 [78] 568 16,488 validation CALFW [79] 5,749 11,652 validation CPLFW [80] 5,749 12,174 validation CFP [81] 500 7,000 validation VGGFace2_test [75] 500 173k validation IJB-B [82] 1,845 76.”
Cross-Resolution Face Recognition via Prior-Aided Face Hallucination and Residual Knowledge Distillation (2019, methodology): “Testing Dataset We evaluate performance of RIM on face hallucination and cross-resolution face recognition over Helen [16], LFW [12], CALFW [33] and CPLFW [20] datasets, respectively.”
Global-Local GCN: Large-Scale Label Noise Cleansing for Face Recognition (2020, methodology): “On the cross-pose and cross-age tests, MS1M-FaceGraph outperforms MS1M by 2.61% on CALFW [56] and 5.44% on CPLFW [55], showing that FaceGraph can master large pose and age gap cases, reserving variations of the same person.”
Exclusivity-Consistency Regularized Knowledge Distillation for Face Recognition (2020, methodology): “– We conduct extensive experiments on a variety of face recognition benchmarks, including LFW [17], CALFW [59], CPLFW [60], SLLFW[8], AgeDB [32], CFP [38], RFW [43], MegaFace [20], Trillion-Pairs [6] and IQIYI-VID [30] have verified the superiority of our approach over the state-of-the-arts.”
CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition (2020, methodology): “We extensively test our method on several popular benchmarks, including LFW [9], CFP-FP [24], CPLFW [41], AgeDB [20], CALFW [40], IJB-B [33], IJB-C [19], and MegaFace [11].”
ArcFace: Additive Angular Margin Loss for Deep Face Recognition (2018, background): “LFW [10] 5,749 13,233 CFP-FP [28] 500 7,000 AgeDB-30 [19] 568 16,488 CPLFW [44] 5,749 11,652 CALFW [45] 5,749 12,174 YTF [38] 1,595 3,425”
ElasticFace: Elastic Margin Loss for Deep Face Recognition (2021, methodology): “CALFW and CPLFW also considered age gaps and pose variation, however, with a lower variation than AgeDB-30 and CFP-6 [14].”
MagFace: A Universal Representation for Face Recognition and Quality Assessment (2021, methodology): “For evaluation, we adopt LFW [14], CFPFP [26], AgeDB-30 [22], CALFW [49], CPLFW [48], IJBB [43] and IJB-C [20] as the benchmarks.”