How far can you get with a modern face recognition test set using only simple features?
Name
Pinto-2009-How far can you get with a modern face recognition test set using only simple features.pdf
Size
470.73 KB
Format
Adobe PDF
Checksum (MD5)
a83732108b1bd748d497e4cbb0e10494
Author(s)
Pinto, Nicolas
DiCarlo, James
Cox, David D.
Date Issued
June 2009
Journal
IEEE Conference on Computer vision and Pettern Recognition
Publisher
Institute of Electrical and Electronics Engineers
Citation
Pinto, N., J.J. DiCarlo, and D.D. Cox. “How far can you get with a modern face recognition test set using only simple features?.” Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on. 2009. 2591-2598. © 2009, IEEE
Version
Final published version
Abstract
In recent years, large databases of natural images have become increasingly popular in the evaluation of face and object recognition algorithms. However, Pinto et al. previously illustrated an inherent danger in using such sets, showing that an extremely basic recognition system, built on a trivial feature set, was able to take advantage of low-level regularities in popular object and face recognition sets, performing on par with many state-of-the-art systems. Recently, several groups have raised the performance "bar" for these sets, using more advanced classification tools. However, it is difficult to know whether these improvements are due to progress towards solving the core computational problem, or are due to further improvements in the exploitation of low-level regularities. Here, we show that even modest optimization of the simple model introduced by Pinto et al. using modern multiple kernel learning (MKL) techniques once again yields "state-of-the-art" performance levels on a standard face recognition set ("labeled faces in the wild"). However, at the same time, even with the inclusion of MKL techniques, systems based on these simple features still fail on a synthetic face recognition test that includes more "realistic" view variation by design. These results underscore the importance of building test sets focussed on capturing the central computational challenges of real-world face recognition.
MIT Department
McGovern Institute for Brain Research at MIT
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/CVPRW.2009.5206605
