DisguiseNet: a contrastive approach for disguised face verification in the wild

Skand Vishwanath Peri, Abhinav Dhall

Research output: Chapter in Book/Report/Conference proceedingConference PaperOther

6 Citations (Scopus)

Abstract

This paper describes our approach for the Disguised Faces in the Wild (DFW) 2018 challenge. The task here is to verify the identity of a person among disguised and impostors images. Given the importance of the task of face verification it is essential to compare methods across a common platform. Our approach is based on VGG-face architecture paired with Contrastive loss based on cosine distance metric. For augmenting the data set, we source more data from the internet. The experiments show the effectiveness of the approach on the DFW data. We show that adding extra data to the DFW dataset with noisy labels also helps in increasing the gen 11 eralization performance of the network. The proposed network achieves 27.13% absolute increase in accuracy over the DFW baseline.

Original languageEnglish
Title of host publicationProceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018
EditorsDavid Forsyth, Ivan Laptev, Deva Ramanan, Aude Oliva
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages25-31
Number of pages7
ISBN (Electronic)9781538661000
ISBN (Print)781538661017
DOIs
Publication statusPublished - 2018
Externally publishedYes
EventDisguised Faces in the Wild 2018 - Salt Lake City, United States of America
Duration: 18 Jun 201822 Jun 2018
http://iab-rubric.org/DFW/index.html

Publication series

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
PublisherIEEE, Institute of Electrical and Electronics Engineers
ISSN (Print)2160-7508
ISSN (Electronic)2160-7516

Conference

ConferenceDisguised Faces in the Wild 2018
Abbreviated titleDFW 2018
CountryUnited States of America
CitySalt Lake City
Period18/06/1822/06/18
Internet address

Cite this

Peri, S. V., & Dhall, A. (2018). DisguiseNet: a contrastive approach for disguised face verification in the wild. In D. Forsyth, I. Laptev, D. Ramanan, & A. Oliva (Eds.), Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018 (pp. 25-31). [8575262] (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/CVPRW.2018.00011