2005 LearningaSimilarityMetricDiscri

• (Chopra et al., 2005) ⇒ Sumit Chopra, Raia Hadsell, and Yann LeCun. (2005). “Learning a Similarity Metric Discriminatively, with Application to Face Verification.” In: Proceedings of 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). ISBN:0-7695-2372-2 doi:10.1109/CVPR.2005.202

Subject Headings: Deep Similarity Neural Network.

Notes

• Google Scholar: https://scholar.google.com/scholar?as_q=Learning+a+similarity+metric+discriminatively%2C+with+application+to+face+verification&as_occt=title&as_sdt=0%2C31
• IEEE: https://ieeexplore.ieee.org/abstract/document/1467314

Cited By

2017

• (Minaee & Liu, 2017) ⇒ Shervin Minaee, and Zhu Liu. (2017). “Automatic Question-Answering Using A Deep Similarity Neural Network.” In: Proceedings of 2017_IEEE Global Conference on Signal and Information Processing (GlobalSIP). doi:10.1109/GlobalSIP.2017.8309095

2014

• (Zhang et al., 2014) ⇒ Junbo Zhang, Guangjian Tian, Yadong Mu, and Wei Fan. (2014). “Supervised Deep Learning with Auxiliary Networks.” In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2014) Journal. ISBN:978-1-4503-2956-9 [http://dx.doi.org/10.1145/2623330.2623618 doi:10.1145/2623330.2623

2012

• (Xiong et al., 2012) ⇒ Caiming Xiong, David Johnson, Ran Xu, and Jason J. Corso. (2012). “Random Forests for Metric Learning with Implicit Pairwise Position Dependence.” In: Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2012). ISBN:978-1-4503-1462-6 [http://dx.doi.org/10.1145/2339530.2339680 doi:10.1145/2339530.2339680

2008a

• (Xiang et al., 2008) ⇒ Shiming Xiang, Feiping Nie, and Changshui Zhang. (2008). “Learning a Mahalanobis Distance Metric for Data Clustering and Classification.” In: Pattern Recognition, 41. doi:10.1016/j.patcog.2008.05.018

2008b

• (Nguyen et al., 2008) ⇒ Nam Nguyen, and Rich Caruana. (2008). “Classification with Partial Labels.” In: Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2008). [http://dx.doi.org/10.1145/1401890.1401958 doi:10.1145/1401890.140195

Quotes

Author Keywords

• Face Recognition; Learning (Artificial Intelligence); similarity metric learning; L1 Norm; Semantic Distance Approximation; Discriminative Loss Function; Geometric Distortion; Character Generation; Drives; Robustness; System.

Abstract

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 L₁ norm in the target space approximates 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

References

;

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2005 LearningaSimilarityMetricDiscri	Yann LeCun Sumit Chopra Raia Hadsell			Learning a Similarity Metric Discriminatively, with Application to Face Verification		Pattern Recognition Task KDD-2008 Proceedings		10.1109/CVPR.2005.202		2005