Similarity Metric Learning for Face Recognition

218 citations recorded by the source corpus.

How researchers see this paper

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

A Theoretical Analysis of Metric Hypothesis Transfer Learning (2015, methodology): “Recently, there is a growing interest for methods able to take into account some background knowledge (Parameswaran & Weinberger, 2010; Cao et al., 2013; Bohné et al., 2014) for learning M.”
Frontal to profile face verification in the wild (2016, methodology): “In restricted settings, Fisher Vector with a metric learning, SubSML [5], achieves 80.”
Labeled Faces in the Wild: A Survey (2016, background): “21 Similarity Metric Learning for Face Recognition, 2013 [23]”
Learning Compact Binary Face Descriptor for Face Recognition (2015, unknown): “Combined Joint Bayesian [9] 90:90 1:48 Sub-SML [7] 90:75 0:64 ConvNet - RBM [53] 91:75 0:48 VMRS+WPCA [3] 92:05 0:45 Fisher vector faces+WPCA [52] 93:03 1:05 High-dim LBP [10] 93:18 1:07 CBFD+WPCA(a) 87:87 1:86 CBFD+WPCA(b) 88:90 1:81 CBFD+WPCA(c) 88:35 1:61 CBFD+WPCA(mean: a, b, c) 90:90 1:40 CBFD+”
Transfer Learning via Learning to Transfer (2018, methodology): “Consequently, we obtain the similarity metric matrix (Cao et al., 2013) ) ) T = X te G ( X te ) T where G is the similarity metric matrix.”
Effective face frontalization in unconstrained images (2014, methodology): “For comparison, the performance originally reported by [4] is also provided.”