Robust Object Recognition with Cortex-Like Mechanisms
IEEE Transactions on Pattern Analysis and Machine Intelligence
Information-theoretic metric learning
Proceedings of the 24th international conference on Machine learning
Fast solvers and efficient implementations for distance metric learning
Proceedings of the 25th international conference on Machine learning
Learning Similarity with Operator-valued Large-margin Classifiers
The Journal of Machine Learning Research
Classification with partial labels
Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining
Learning a Mahalanobis distance metric for data clustering and classification
Pattern Recognition
A Subspace Method Based on Data Generation Model with Class Information
Neural Information Processing
Improving Classification with Pairwise Constraints: A Margin-Based Approach
ECML PKDD '08 Proceedings of the European conference on Machine Learning and Knowledge Discovery in Databases - Part II
Metric Learning: A Support Vector Approach
ECML PKDD '08 Proceedings of the European conference on Machine Learning and Knowledge Discovery in Databases - Part II
Feature selection based on loss-margin of nearest neighbor classification
Pattern Recognition
Deep learning from temporal coherence in video
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
International Journal of Approximate Reasoning
International Journal of Knowledge Engineering and Soft Data Paradigms
MM '09 Proceedings of the 17th ACM international conference on Multimedia
Learning term-weighting functions for similarity measures
EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 2 - Volume 2
Biometric person authentication is a multiple classifier problem
MCS'07 Proceedings of the 7th international conference on Multiple classifier systems
Generalized iterative RELIEF for supervised distance metric learning
Pattern Recognition
Edited AdaBoost by weighted kNN
Neurocomputing
Multiple instance metric learning from automatically labeled bags of faces
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
Adapting visual category models to new domains
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Predicting facial beauty without landmarks
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part VI
Semi-supervised metric learning for image classification
PCM'10 Proceedings of the Advances in multimedia information processing, and 11th Pacific Rim conference on Multimedia: Part II
Nearest neighbour distance matrix classification
ADMA'10 Proceedings of the 6th international conference on Advanced data mining and applications: Part I
A multi-scale learning framework for visual categorization
ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part I
Learning discriminative projections for text similarity measures
CoNLL '11 Proceedings of the Fifteenth Conference on Computational Natural Language Learning
Effective diagnosis of alzheimer's disease by means of distance metric learning
HAIS'11 Proceedings of the 6th international conference on Hybrid artificial intelligent systems - Volume Part I
Relation learning: a new approach to face recognition
ACIVS'11 Proceedings of the 13th international conference on Advanced concepts for intelligent vision systems
On the expressive power of deep architectures
ALT'11 Proceedings of the 22nd international conference on Algorithmic learning theory
Face Recognition from Caption-Based Supervision
International Journal of Computer Vision
Facing scalability: Naming faces in an online social network
Pattern Recognition
Distance metric learning with eigenvalue optimization
The Journal of Machine Learning Research
Metric and kernel learning using a linear transformation
The Journal of Machine Learning Research
Statistical Analysis and Data Mining
Random forests for metric learning with implicit pairwise position dependence
Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining
Nearest neighbor classifier generalization through spatially constrained filters
Pattern Recognition
k nearest neighbor using ensemble clustering
DaWaK'12 Proceedings of the 14th international conference on Data Warehousing and Knowledge Discovery
Supervised earth mover's distance learning and its computer vision applications
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part I
Distance metric learning revisited
ECML PKDD'12 Proceedings of the 2012 European conference on Machine Learning and Knowledge Discovery in Databases - Volume Part I
Mirror descent for metric learning: a unified approach
ECML PKDD'12 Proceedings of the 2012 European conference on Machine Learning and Knowledge Discovery in Databases - Volume Part I
Local distance comparison for multiple-shot people re-identification
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III
Human-virtual human interaction by upper body gesture understanding
Proceedings of the 19th ACM Symposium on Virtual Reality Software and Technology
Discovering common motifs in cursor movement data for improving web search
Proceedings of the 7th ACM international conference on Web search and data mining
An ensemble-clustering-based distance metric and its applications
International Journal of Business Intelligence and Data Mining
Hi-index | 0.00 |
We present a method for training a similarity metric from data. The method can be used for recognition or verification applications where the number of categories is very large and not known during training, and where the number of training samples for a single category is very small. The idea is to learn a function that maps input patterns into a target space such that the L驴 norm in the target spaceapproximates the "semantic" distance in the input space. The method is applied to a face verification task. The learning process minimizes a discriminative loss function that drives the similarity metric to be small for pairs of faces from the same person, and large for pairs from different persons. The mapping from raw to the target space is a convolutional network whose architecture is designed for robustness to geometric distortions. The system is tested on the Purdue/AR face database which has a very high degree of variability in the pose, lighting, expression, position, and artificial occlusions such as dark glasses and obscuring scarves.