Deep Localized Metric Learning
- 1 June 2017
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 28 (10) , 2644-2656
Abstract
Metric learning has been widely used in many visual analysis applications, which learns new distance metrics to measure the similarities of samples effectively. Conventional metric learning methods learn a single linear Mahalanobis metric, yet such linear projections are not powerful enough to capture the nonlinear relationships. Recently, deep metric learning approaches, such as discriminative deep metric learning and deep transfer metric learning, have been introduced to fully exploit the nonlinearity of samples by learning hierarchical nonlinear transformations. However, these methods only learn holistic metrics over the input space and are limited for the heterogeneous data sets, where data varies locally. In this paper, we propose a deep localized metric learning approach for visual recognition by learning multiple fine-grained deep localized metrics. We first learn K local subspaces and one holistic subspace with the K-auto-encoders-based clustering. Then, given an input pair, we compute its localized distance on each learned subspace and obtain the final distance representation. Finally, we train the entire neural networks to ensure the distances of positive pairs smaller than negative pairs by a large margin. Experimental results on three visual recognition applications, including face recognition, person re-identification, and scene recognition, show that our DLML outperforms most existing metric learning approaches.Keywords
Funding Information
- National Key Research and Development Program of China (2016YFB1001001)
- National Natural Science Foundation of China (61672306, 61572271, 61527808, 61373074, 61373090)
- National 1000 Young Talents Plan Program
- National Basic Research Program of China (2014CB349304)
- Ministry of Education of China (20120002110033)
- Tsinghua University
This publication has 54 references indexed in Scilit:
- Localized Multifeature Metric Learning for Image-Set-Based Face RecognitionIEEE Transactions on Circuits and Systems for Video Technology, 2015
- Learning Compact Binary Face Descriptor for Face RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- A Kernel Classification Framework for Metric LearningIEEE Transactions on Neural Networks and Learning Systems, 2014
- Person Re-Identification Over Camera Networks Using Multi-Task Distance Metric LearningIEEE Transactions on Image Processing, 2014
- Covariance descriptor based on bio-inspired features for person re-identification and face verificationImage and Vision Computing, 2014
- Learning Prototype Hyperplanes for Face Verification in the WildIEEE Transactions on Image Processing, 2013
- Fisher Vector Faces in the Wild2013
- Multiple-shot person re-identification by chromatic and epitomic analysesPattern Recognition Letters, 2012
- Information-theoretic metric learning2007
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004