Discriminative Deep Metric Learning for Face Verification in the Wild
Authors:
- Junlin HuJunlin Hu
- Jiwen LuJLJiwen Lu
- Yap-Peng TanYTYap-Peng Tan
Top Cited Papers
- 1 June 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1875-1882
Abstract
This paper presents a new discriminative deep metric learning (DDML) method for face verification in the wild. Different from existing metric learning-based face verification methods which aim to learn a Mahalanobis distance metric to maximize the inter-class variations and minimize the intra-class variations, simultaneously, the proposed DDML trains a deep neural network which learns a set of hierarchical nonlinear transformations to project face pairs into the same feature subspace, under which the distance of each positive face pair is less than a smaller threshold and that of each negative pair is higher than a larger threshold, respectively, so that discriminative information can be exploited in the deep network. Our method achieves very competitive face verification performance on the widely used LFW and YouTube Faces (YTF) datasets.Keywords
This publication has 30 references indexed in Scilit:
- The SVM-Minus Similarity Score for Video Face Recognition2013
- Towards Pose Robust Face Recognition2013
- Learning hierarchical representations for face verification with convolutional deep belief networks2012
- 3D Convolutional Neural Networks for Human Action RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Face recognition in unconstrained videos with matched background similarity2011
- Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis2011
- Sparse approximated nearest points for image set classification2011
- Discriminative Learning and Recognition of Image Set Classes Using Canonical CorrelationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998