Adaptive Deep Metric Learning for Identity-Aware Facial Expression Recognition

Xiaofeng Liu, B. V.K.Vijaya Kumar, Jia You, Ping Jia

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

114 Citations (Scopus)

Abstract

A key challenge of facial expression recognition (FER) is to develop effective representations to balance the complex distribution of intra- and inter- class variations. The latest deep convolutional networks proposed for FER are trained by penalizing the misclassification of images via the softmax loss. In this paper, we show that better FER performance can be achieved by combining the deep metric loss and softmax loss in a unified two fully connected layer branches framework via joint optimization. A generalized adaptive (N+M)-tuplet clusters loss function together with the identity-aware hard-negative mining and online positive mining scheme are proposed for identity-invariant FER. It reduces the computational burden of deep metric learning, and alleviates the difficulty of threshold validation and anchor selection. Extensive evaluations demonstrate that our method outperforms many state-of-art approaches on the posed as well as spontaneous facial expression databases.
Original languageEnglish
Title of host publicationProceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
PublisherIEEE Computer Society
Pages522-531
Number of pages10
Volume2017-July
ISBN (Electronic)9781538607336
DOIs
Publication statusPublished - 22 Aug 2017
Event30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017 - Honolulu, United States
Duration: 21 Jul 201726 Jul 2017

Conference

Conference30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
Country/TerritoryUnited States
CityHonolulu
Period21/07/1726/07/17

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this