Is that you? Metric learning approaches for face identification

By Matthieu Guillaumin, Jakob Verbeek, Cordelia Schmid. 2009

927 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

Deep Meta-Learning: Learning to Learn in the Concept Space (2018, methodology): “Other methods use metric learning to ease pairwise comparison between examples (Fink, 2005; Koch, 2015; Guillaumin et al., 2009; Schroff et al., 2015).”
Deep Learning Face Representation by Joint Identification-Verification (2014, background): “For example, metric learning [6, 9, 15] maps faces to some feature representation such that faces of the same identity are close to each other while those of different identities stay apart.”
Beyond frontal faces: Improving Person Recognition using multiple cues (2015, background): “Existing work is mainly focused on metric learning [27, 17, 22], mid-level feature learning [16, 39, 40, 10, 20, 26].”
A Survey on Metric Learning for Feature Vectors and Structured Data (2013, background): “…vision problems, such as image classification (Mensink et al., 2012), object recognition (Frome et al., 2007; Verma et al., 2012), face recognition (Guillaumin et al., 2009b; Lu et al., 2012), visual tracking (Li et al., 2012; Jiang et al., 2012) or image annotation (Guillaumin et al., 2009a).”
Deeply learned face representations are sparse, selective, and robust (2014, background): “While pursuing higher performance is a central topic, understanding the mechanisms behind it is equally important.”
Person Recognition in Personal Photo Collections (2015, background): “Both settings have seen a recent shift from sophisticated classifiers based on hand-crafted features and metric learning approaches [20, 7, 5, 29, 26, 41, 1], towards methods based on deep learning [37, 36, 43, 33, 27, 38, 21].”
Deep Learning for Content-Based Image Retrieval: A Comprehensive Study (2014, background): “Distance metric learning for image retrieval has been extensively studied in both machine learning and multimedia retrieval communities [12, 2, 48, 29, 15, 47, 33, 46].”
PersonNet: Person Re-identification with Deep Convolutional Neural Networks (2016, methodology): “Among many metric learning methods, Large Margin Nearest Neighbor Learning (LMNN) [33], Information Theoretic Metric Learning (ITML) [34], and Logistic Discriminant Metric Learning (LDM) [35] are three representative methods.”
End-to-End Comparative Attention Networks for Person Re-Identification (2016, methodology): “We compare our model with the following state-of-the-art methods: SDALF [4], LMNN [5], ITML [1], KRMCA [22], LDM [3] , eSDC [10], Metric Ensembles (Ensembles) [8], KISSME [7], JointRe-id [16], FPNN [13], PersonNet [17].”
Joint Learning of Single-Image and Cross-Image Representations for Person Re-identification (2016, methodology): “We also compare the performances of the proposed method and some other state−of−the−art methods, including Euclidean distance, ITML [5], LMNN [35], metric learn− ing to rank (RANK) [27], LDML [13], symmetry−driven 0 1 2 3 4 5 0.”
When Face Recognition Meets with Deep Learning: An Evaluation of Convolutional Neural Networks for Face Recognition (2015, methodology): “The results in Table 6 show that our method is better than [27, 8, 16] but worse than [7, 19, 23].”
Active learning and discovery of object categories in the presence of unnameable instances (2015, methodology): “In our experiments, we use the face features provided by [13] consisting of SIFT descriptors extracted at nine detected landmark positions and three different scales.”
Locally Aligned Feature Transforms across Views (2013, neutral): “9 76 87 LDML[12][19] 10.”
Cosine Similarity Metric Learning for Face Verification (2010, background): “Each type of feature is tested with the original feature vector or the square root of the feature vector [8,14,20].”
Cross-Modal Similarity Learning: A Low Rank Bilinear Formulation (2014, background): “The loss function (Guillaumin, Verbeek, and Schmid 2009) is based on the logistic sigmoid function, δ ( x ) = 1 / (1 + exp( − x )) , which is often integrated in − log( δ ( x )) to approximate the hinge loss function to avoid the discontinuity of the gradient.”
Heated-Up Softmax Embedding (2018, background): “, 2017), face recognition (Guillaumin et al., 2009; Schroff et al., 2015), and person re-identification (Koestinger et al.”
Metric Learning: A Survey (2013, methodology): “A recent paper [30] considered an approach to face recognition based on Mahalanobis distances.”
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].”