Minimum margin loss for deep face recognition

Xin Wei, H. Wang, Bryan Scotney, Huan Wan

Research output: Contribution to journalArticlepeer-review

25 Citations (Scopus)
106 Downloads (Pure)


Face recognition has achieved great success owing to the fast development of deep neural networks in the past few years. Different loss functions can be used in a deep neural network resulting in different performance. Most recently some loss functions have been proposed, which have advanced the state of the art. However, they cannot solve the problem of margin bias which is present in class imbalanced datasets, having the so-called long-tailed distributions. In this paper, we propose to solve the margin bias problem by setting a minimum margin for all pairs of classes. We present a new loss function, Minimum Margin Loss (MML), which is aimed at enlarging the margin of those overclose class centre pairs so as to enhance the discriminative ability of the deep features. MML, together with Softmax Loss and Centre Loss, supervises the training process to balance the margins of all classes irrespective of their class distributions. We implemented MML in Inception-ResNet-v1 and conducted extensive experiments on seven face recognition benchmark datasets, MegaFace, FaceScrub, LFW, SLLFW, YTF, IJB-B and IJB-C. Experimental results show that the proposed MML loss function has led to new state of the art in face recognition, reducing the negative effect of margin bias.
Original languageEnglish
Article number107012
Number of pages9
JournalPattern Recognition
Early online date17 Aug 2019
Publication statusPublished (in print/issue) - 31 Jan 2020


  • Deep learning
  • Convolutional neural networks
  • Face recognition
  • Minimum Margin Loss
  • Minimum margin loss


Dive into the research topics of 'Minimum margin loss for deep face recognition'. Together they form a unique fingerprint.

Cite this