Latent Factor Guided Convolutional Neural Networks for Age-Invariant Face Recognition

By Yandong Wen, Zhifeng Li, Yu Qiao. 2016

171 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

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

SphereFace: Deep Hypersphere Embedding for Face Recognition (2017, background): “In general, current well-performing CNNs [30, 27, 16, 36] for FR are mostly built on either contrastive loss or triplet loss.”
A Discriminative Feature Learning Approach for Deep Face Recognition (2016, background): “Recently, contrastive loss [29,37] and triplet loss [27] are also proposed to enhance the discriminative power of the deeply learned face features.”
Marginal Loss for Deep Face Recognition (2017, result): “As can be seen from Table 2, the proposed marginal loss significantly outperforms all the published results [4, 6, 3, 26] on this dataset, even surpassing the human-level performance with a clear margin.”
Cross-Domain Similarity Learning for Face Recognition in Unseen Domains (2021, methodology): “In all comparisons, our method outperforms the previous work of LF-CNNs [45].”
A Comprehensive Study on Center Loss for Deep Face Recognition (2019, methodology): “– Compared to contrastive loss and triplet loss Contrastive loss (Sun et al. 2014a; Wen et al. 2016a) and triplet loss (Schroff et al. 2015) are proposed to enhance the discriminative power of the deeply learned face features.”
L2-constrained Softmax Loss for Discriminative Face Verification (2017, methodology): “Due to this reason, many methods either apply metric learning on top of softmax features [27, 3, 24] or train an auxiliary loss [33, 29, 32] along with the softmax loss to achieve better veriﬁcation performance.”
Learning Meta Face Recognition in Unseen Domains (2020, unknown): “ition problem. GFR-V (CACD-VS) VR (%) Rank-1 (%) Acc. AUC. FAR=0.01% FAR=0.001% Base 96.55 92.55 96.85 99.35 99.53 Base-Agg 96.75 92.98 97.15 99.42 99.6 MLDG [14] 96.75 92.9 97.25 99.45 99.57 LF-CNNs [39] - - - 98.5 99.3 Human, Voting [40] - - - 94.2 99 OE-CNNs [41] - - - 99.2 99.5 AIM+CAFR [42] - -”
Range Loss for Deep Face Recognition with Long-Tailed Training Data (2016, background): “Deep neural networks with great ability to learning representation from data, achieve remarkable successes in a series of vision tasks like recognition and detection [6, 24, 15, 7, 28], face recognition [20, 23, 26, 2, 33, 18, 30].”
Deep Face Recognition: A Survey (2018, background): “[172] developed a latent identity analysis (LIA) layer to separate the two components (Fig.”