Distance Metric Learning: A Comprehensive Survey

By Liu Yang, Rong Jin. 2006

Subfields: Representation & Self-Supervised Learning

How researchers see this paper

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

In Representation & Self-Supervised Learning

Citations in the corpus

UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction (2018, background): “Finally, there are many use cases for metric learning; see [54] or [7] for example.”
A Survey on Metric Learning for Feature Vectors and Structured Data (2013, background): “The early review due to Yang and Jin (2006) is now largely outdated as it misses out on important recent advances: more than 75% of the work referenced in the present survey is post 2006.”
A survey of approaches and trends in person re-identification (2014, unknown): “Distance Metric learning methods [88] are extensively explored in the recognition and image retrieval problems, and they”
A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities (2022, background): “On this basis, many works [124], [125], [126], [127], [128] have explored how to make the distance between prototypes larger and larger.”
Learning to rank in person re-identification with metric ensembles (2015, unknown): “Contents”
Survey on distance metric learning and dimensionality reduction in data mining (2014, background): “In recent years, many studies have demonstrated Kulis (2010), Werman et al. (2010), and Yang and Jin (2006), either theoretically or empirically, that learning a good distance metric can greatly improve the performance of classification (Weinberger and Saul 2009), clustering (Domeniconi et al.…”
Maximum Neighborhood Margin Discriminant Projection for Classification (2014, methodology): “We first analyze the affinity weight for intraclass and interclass neighborhoods, then discuss the MNMDP from the viewpoint of distance metric learning [50, 51], and finally explore the eigenvalues of the generalized eigenvalue problem in MNMDP.”
Similarity Metric Learning for Face Recognition (2013, background): “Metric learning [5,7,22,25,26] usually focuses on the (squared) Mahalanobis distance defined, for any x, t ∈ R, by dM (x, t) = (x − t)M(x − t), where M is a positive semi-definite (p.”
Online multimodal deep similarity learning with application to image retrieval (2013, methodology): “Although a variety of DML algorithms have been proposed [50], most existing DML methods suffer from two critical limitations: (i) They usually learn a linear distance metric in the forms of Mahalanobis distances, which can be viewed as learning a linear projection to map feature vectors into…”
Distance Metric Learning with Eigenvalue Optimization (2012, background): “We refer the readers to Yang and Jin (2007) for a nice survey on metric learning.”
Person Re-identification: Past, Present and Future (2016, methodology): “This method belongs to the supervised local distance metric learning category [53].”
Learning a Discriminative Null Space for Person Re-identification (2016, methodology): “Distance metric learning has been extensively studied in machine learning [37], and existing metric learning methods employed for re-id are either originated elsewhere or extensions of existing methods with modifications to address the additional challenges arising from the re-id task.”
Regularized Distance Metric Learning: Theory and Algorithm (2009, background): “Although a large number of studies were devoted to supervised distance metric learning (see the survey in [18] and references therein), few studies address the generalization error of distance metric learning.”
A Survey of Modern Questions and Challenges in Feature Extraction (2015, background): “This brings us to an important area of feature extraction - distance metric learning (Yang and Jin, 2006).”
Fixed-dimensional acoustic embeddings of variable-length segments in low-resource settings (2013, background): “Such embeddings would (i) enable the application of standard distance learning techniques [5, 6] to template-based acoustic modeling and (ii) support a new generation of efficient segment-based audio indexing algorithms, enabling highly scalable spoken term discovery [7, 8, 9] and query-by-example s”
Large Scale Online Learning of Image Similarity Through Ranking (2009, background): “A large number of previous studies have focused on learning a similarity measure that is also a metric, like in the case of a positive semidefinite matrix that defines a Mahalanobis distance (Yang, 2006).”
Learning Locally-Adaptive Decision Functions for Person Verification (2013, background): “Recently, metric learning (ML) approaches [26] have been applied to person veriﬁcation [12, 19, 6, 2].”
Linear dimensionality reduction: survey, insights, and generalizations (2014, methodology): “, 2001), linear regression, distance metric learning (DML; Kulis, 2012; Yang and Jin, 2006), probabilistic PCA (PPCA; Tipping and Bishop, 1999; Roweis, 1997; Theobald, 1975), factor analysis (FA; Spearman, 1904), several related methods, and important extensions such as kernel mappings and regulariz”