Personal tools

Simple Triplet Loss Based on Intra/Inter-class Metric Learning for Face Verification

From LRDE

Jump to: navigation, search

Abstract

Recently, benefiting from the advances of the deep convolution neural networks (CNNs), significant progress has been made in the field of the face verification and face recognition. Specially, the performance of the FaceNet has overpassed the human level performance in terms of the accuracy on the datasets Labeled Faces in the Wild (LFW) and Youtube Faces in the Wild (YTF) The triplet loss used in the FaceNet has proved its effectiveness for face verification. However, the number of the possible triplets is explosive when using a large scale dataset to train the model. In this paper, we propose a simple class-wise triplet loss based on the intra/inter-class distance metric learning which can largely reduce the number of the possible triplets to be learned. However the simplification of the classic triplet loss function has not degraded the performance of the proposed approach. The experimental evaluations on the most widely used benchmarks LFW and YTF show that the model with the proposed class-wise simple triplet loss can reach the state-of-the-art performance. And the visualization of the distribution of the learned features based on the MNIST dataset has also shown the effectiveness of the proposed method to better separate the classes and make the features more discriminative in comparison with the other state-of-the-art loss function.


Bibtex (lrde.bib)

@InProceedings{	  ming.17.iccv-amfg,
  title		= {Simple Triplet Loss Based on Intra/Inter-class Metric
		  Learning for Face Verification},
  author	= {Zuheng Ming and Joseph Chazalon and Muhammad Muzzamil
		  Luqman and Muriel Visani and Jean-Christophe Burie},
  booktitle	= {Proceedings of the 7th IEEE Workshop on Analysis and
		  Modeling of Faces and Gestures, ICCV-AMFG},
  year		= {2017},
  note		= {to appear.},
  abstract	= {Recently, benefiting from the advances of the deep
		  convolution neural networks (CNNs), significant progress
		  has been made in the field of the face verification and
		  face recognition. Specially, the performance of the FaceNet
		  has overpassed the human level performance in terms of the
		  accuracy on the datasets Labeled Faces in the Wild (LFW)
		  and Youtube Faces in the Wild (YTF) The triplet loss used
		  in the FaceNet has proved its effectiveness for face
		  verification. However, the number of the possible triplets
		  is explosive when using a large scale dataset to train the
		  model. In this paper, we propose a simple class-wise
		  triplet loss based on the intra/inter-class distance metric
		  learning which can largely reduce the number of the
		  possible triplets to be learned. However the simplification
		  of the classic triplet loss function has not degraded the
		  performance of the proposed approach. The experimental
		  evaluations on the most widely used benchmarks LFW and YTF
		  show that the model with the proposed class-wise simple
		  triplet loss can reach the state-of-the-art performance.
		  And the visualization of the distribution of the learned
		  features based on the MNIST dataset has also shown the
		  effectiveness of the proposed method to better separate the
		  classes and make the features more discriminative in
		  comparison with the other state-of-the-art loss function.}
}