Distance Metric Learning with Eigenvalue Optimization

By Yiming Ying, Peng Li. 2012

335 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

Citations in the corpus

SphereFace: Deep Hypersphere Embedding for Face Recognition (2017, background): “Traditional metric learning [36, 33, 12, 38] usually learns a matrix A for a distance metric ‖x1−x2‖A= √ (x1−x2)A(x1−x2) upon the given features x1,x2.”
A Survey on Metric Learning for Feature Vectors and Structured Data (2013, background): “ability of the approach, while Liu and Vemuri (2012) introduce regularization on the weights as well as a term to reduce redundancy among the weak learners. DML-p(Ying et al., Cao et al.) The work of Ying and Li (2012); Cao et al. (2012b) revisit MMC, the original approach of Xing et al. (2002), by ”
Discriminative Deep Metric Learning for Face Verification in the Wild (2014, methodology): “These compared methods can be categorized two classes: 1) metric learning based methods such as LDML [9], PCCA [25], CSML+SVM [26], DML-eig combined [40], and STFRD+PMML [6]; and 2) descriptor based methods such as Multiple LE+comp [4], Pose Adaptive Filter (PAF) [39], and Fisher vector faces [28].”
Geometry preserving multi-task metric learning (2012, background): “Speci(cid:28)cally, assume that we have two metric learning tasks to learn Mahalanobis matrices A and B respectively.”
Learning Locally-Adaptive Decision Functions for Person Verification (2013, methodology): “MERL+Nowak [14] 76.2 LDML [12] 79.3 LBP + CSML [19] 85.6 CSML + SVM [19] 88.0 Combined b/g samples [25] 86.8 DML-eig combined [27] 85.7 Deep Learning combined [15] 87.8 Our method 89.6 the best reported results 3 in LFW under the category of “no outside data is used beyond alignment/feature…”
Labeled Faces in the Wild: A Survey (2016, methodology): “14 Distance Metric Learning with Eigenvalue Optimization, 2012 [111]”
Metric Learning: A Survey (2013, background): “Another recent paper showed that several Mahalanobis metric learning methods can be shown to be equivalent to a problem of minimizing the maximal eigenvalue of a symmetric matrix [83]; this yields new algorithms for existing models, such as LMNN, as well as new formulations.”
Fisher Vector Faces in the Wild (2013, background): “The question that this paper addresses is what happens if, instead of developing yet another face-specific image representation, one applies off-the-shelf object recognition representations to AFV.”
Tom-vs-Pete Classifiers and Identity-Preserving Alignment for Face Verification (2012, methodology): “Funneled images provided by the LFW maintainers have been widely used [12, 17, 26, 32, 35], but the Tom-vs-Pete classifiers require a correspondence more precise than funneling provides.”
Linear-Memory and Decomposition-Invariant Linearly Convergent Conditional Gradient Algorithm for Structured Polytopes (2016, methodology): “It has been recently shown that the method delivers state-of-the-art performance on many problems of interest, see for instance [14, 17, 4, 10, 11, 22, 19, 25, 12, 15].”
Similarity Metric Learning for Face Recognition (2013, methodology): “Below we review metric learning models [11, 22, 25, 27] which are closely related to our proposed method Sub-SML, and show the inherent relationship among these models.”
Reconstructing Capsule Networks for Zero-shot Intent Classification (2019, methodology): “As shown by Ying and Li (2012), optimizing Eq.”
Decomposition Techniques for Bilinear Saddle Point Problems and Variational Inequalities with Affine Monotone Operators (2015, methodology): “To the best of our knowledge, the related results reduce to LMO-based techniques for large-scale NCM based on Nesterov’s smoothing [1, 20, 23, 24, 4, 18].”
Bayesian Face Revisited: A Joint Formulation (2012, background): “Metric learning [7–10, 21] has recently attracted a lot of attentions in face recognition.”