2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016
DOI: 10.1109/cvpr.2016.527
|View full text |Cite
|
Sign up to set email alerts
|

The MegaFace Benchmark: 1 Million Faces for Recognition at Scale

Abstract: Recent face recognition experiments on a major benchmark (LFW [14]) show stunning performance-a number of algorithms achieve near to perfect score, surpassing human recognition rates. In this paper, we advocate evaluations at the million scale (LFW includes only 13K photos of 5K people). To this end, we have assembled the MegaFace dataset and created the first MegaFace challenge. Our dataset includes One Million photos that capture more than 690K different individuals. The challenge evaluates performance of al… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
594
0

Year Published

2016
2016
2022
2022

Publication Types

Select...
4
3
3

Relationship

0
10

Authors

Journals

citations
Cited by 815 publications
(594 citation statements)
references
References 41 publications
0
594
0
Order By: Relevance
“…However, the MegaFace Challenge [51] does start to investigate what happens to the performance of face recognition algorithms when the person to be recognized is mixed with up to a million distractors that were not in the training set. It was found that all algorithms had lower recognition accuracy when they were tested on the MegaFace dataset.…”
Section: Discussionmentioning
confidence: 99%
“…However, the MegaFace Challenge [51] does start to investigate what happens to the performance of face recognition algorithms when the person to be recognized is mixed with up to a million distractors that were not in the training set. It was found that all algorithms had lower recognition accuracy when they were tested on the MegaFace dataset.…”
Section: Discussionmentioning
confidence: 99%
“…This is exactly the type of problem that an officer wearing the advanced vest would be faced with in trying to use facial recognition in the field. They found that those algorithms trained on larger sets of data performed better (Kemelmacher-Shlizerman et al, 2016). However, this is still an active field of research.…”
Section: Performance Of Facial Recognition Systemsmentioning
confidence: 99%
“…Despite promising performance of automatic face recognition algorithms in a controlled setting (Kemelmacher-Shlizerman et al, 2015), many applications require accurate identification at planetary scale, i.e., finding the best matching face in a database of millions of people. For instance, face recognition algorithms failed to identify criminals in the Boston marathon bombing (Klontz et al, 2013).…”
Section: The Role Of Biometric Technology In Forensicsmentioning
confidence: 99%