Large Scale Strongly Supervised Ensemble Metric Learning, with Applications to Face Verification and Retrieval
Explore this paper's citation graph
Summary
An ensemble metric learning approach that consists of sparse block diagonal metric ensembling and join- t metric learning as two consecutive steps that outperform existing state-of-the-art methods in accuracy while retaining high efficiency in face verification and retrieval.
- Type
- preprint
- Published
- 2012-12-25
- Cited by
- 72
- References
- 23
- Access
- Open access
- OpenAlex
- https://openalex.org/W1854859904
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:2615167
Keywords
Metric (unit), Pairwise comparison, Computer science, Feature (linguistics), Ensemble learning
References
- Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments
- A decision-theoretic generalization of on-line learning and an application to boosting
- Multiple One-Shots for Utilizing Class Label Information
- THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS
- Fast alternating linearization methods for minimizing the sum of two convex functions
- Metric Learning by Collapsing Classes
- Sparse coding with an overcomplete basis set: a strategy employed by V1?
- Distance Metric Learning for Large Margin Nearest Neighbor Classification
- Is that you? Metric learning approaches for face identification
- Pedestrian Detection via Classification on Riemannian Manifolds
- Distance Metric Learning with Application to Clustering with Side-Information
- An efficient sparse metric learning in high-dimensional space via l1-penalized log-determinant regularization
- Semi-supervised sparse metric learning using alternating linearization optimization
- Learning Distance Metrics with Contextual Constraints for Image Retrieval
- Neighbourhood Components Analysis
- Matching pursuits with time-frequency dictionaries
- Learning Distance Functions using Equivalence Relations
- Probabilistic Models for Inference about Identity
- Leveraging Billions of Faces to Overcome Performance Barriers in Unconstrained Face Recognition
- Information-theoretic metric learning
Cited by
- Face Retrieval on Large-Scale Video Data
- Unsupervised learning of overcomplete face descriptors
- Deeply learned face representations are sparse, selective, and robust
- Fisher Vector Faces in the Wild
- Deep nonlinear metric learning with independent subspace analysis for face verification
- Maximizing face recognition performance for video data under time constraints by using a cascade
- Deep Learning Face Representation from Predicting 10,000 Classes
- Nonlinear Metric Learning with Deep Independent Subspace Analysis Network for Face Verification
- Tom-vs-Pete Classifiers and Identity-Preserving Alignment for Face Verification
- Person-Specific Subspace Analysis for Unconstrained Familiar Face Identification
- Modular hierarchical feature learning with deep neural networks for face verification
- Vehicle Detection in Satellite Images by Parallel Deep Convolutional Neural Networks
- Fisher's linear discriminant embedded metric learning
- Sparse Variation Pattern for Texture Classification
- Multi scale multi descriptor local binary features and exponential discriminant analysis for robust face authentication
- Multiscale Local Phase Quantization for Robust Component-Based Face Recognition Using Kernel Fusion of Multiple Descriptors
- PFW: A Face Database in the Wild for Studying Face Identification and Verification in Uncontrolled Environment
- Fast High Dimensional Vector Multiplication Face Recognition
- Blessing of Dimensionality: High-Dimensional Feature and Its Efficient Compression for Face Verification
- Hybrid Deep Learning for Face Verification
Related papers
- The validity of pairwise models in predicting community dynamics
- Non-pairwise Collaborative Filtering
- Pairwise semiregular properties on generalized pairwise regular-Lindelof spaces.
- Comparing Apples and Oranges: Taxonomy and Design of Pairwise Comparisons within Tabular Data
- Lotka-Volterra pairwise modeling fails to capture diverse pairwise microbial interactions
- Estimating manifold dimension with nearest neighbor graphs