Skip to main navigation Skip to search Skip to main content

The do's and don'ts for CNN-Based face verification

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

Abstract

While the research community appears to have developed a consensus on the methods of acquiring annotated data, design and training of CNNs, many questions still remain to be answered. In this paper, we explore the following questions that are critical to face recognition research: (i) Can we train on still images and expect the systems to work on videos? (ii) Are deeper datasets better than wider datasets? (iii) Does adding label noise lead to improvement in performance of deep networks? (iv) Is alignment needed for face recognition? We address these questions by training CNNs using CASIA-WebFace, UMD-Faces, and a new video dataset and testing on YouTube-Faces, IJB-A and a disjoint portion of UMDFaces datasets. Our new data set, which will be made publicly available, has 22,075 videos and 3,735,476 human annotated frames extracted from them.

Original languageEnglish (US)
Title of host publicationProceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2545-2554
Number of pages10
ISBN (Electronic)9781538610343
DOIs
StatePublished - Jul 1 2017
Externally publishedYes
Event16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017 - Venice, Italy
Duration: Oct 22 2017Oct 29 2017

Publication series

NameProceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017
Volume2018-January

Conference

Conference16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017
Country/TerritoryItaly
CityVenice
Period10/22/1710/29/17

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'The do's and don'ts for CNN-Based face verification'. Together they form a unique fingerprint.

Cite this