Outlier-Suppressed Triplet Loss with Adaptive Class-Aware Margins for Facial Expression Recognition

Yi Tian, Zhiwei Wen, Weicheng Xie, Xi Zhang, Linlin Shen, Jinming Duan

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

6 Citations (Scopus)

Abstract

Triplet loss has been proposed to increase the inter-class distance and decrease the intra-class distance for various tasks of image recognition. However, for facial expression recognition (FER) problem, the fixed margin parameter does not fit the diversity of scales between different expressions. Meanwhile, the strategy of selecting the hardest triplets can introduce noisy guidance information since various persons may present significantly different expressions. In this work, we propose a new triplet loss based on class-aware margins and outlier-suppressed triplet for FER, where each pair of expressions, e.g. 'happy' and 'fear', is assigned with an adaptive margin parameter and the abnormal hard triplets are discarded according to the feature distance distribution. Experimental results of the proposed triplet loss on the FER2013 and CK+ expression databases show that the proposed network achieves much better accuracy than the original triplet loss and the network without using the proposed strategies, and competitive performance compared with the state-of-the-art algorithms.

Original languageEnglish
Title of host publication2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
PublisherIEEE Computer Society
Pages46-50
Number of pages5
ISBN (Electronic)9781538662496
DOIs
Publication statusPublished - Sep 2019
Externally publishedYes
Event26th IEEE International Conference on Image Processing, ICIP 2019 - Taipei, Taiwan, Province of China
Duration: 22 Sep 201925 Sep 2019

Publication series

NameProceedings - International Conference on Image Processing, ICIP
Volume2019-September
ISSN (Print)1522-4880

Conference

Conference26th IEEE International Conference on Image Processing, ICIP 2019
Country/TerritoryTaiwan, Province of China
CityTaipei
Period22/09/1925/09/19

Keywords

  • class-aware margin
  • facial expression recognition
  • outlier suppression
  • triplet loss

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Fingerprint

Dive into the research topics of 'Outlier-Suppressed Triplet Loss with Adaptive Class-Aware Margins for Facial Expression Recognition'. Together they form a unique fingerprint.

Cite this