DeepFace: Closing the Gap to Human-Level Performance in Face Verification
Top Cited Papers
- 1 June 2014
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1701-1708
- https://doi.org/10.1109/cvpr.2014.220
Abstract
In modern face recognition, the conventional pipeline consists of four stages: detect => align => represent => classify. We revisit both the alignment step and the representation step by employing explicit 3D face modeling in order to apply a piecewise affine transformation, and derive a face representation from a nine-layer deep neural network. This deep network involves more than 120 million parameters using several locally connected layers without weight sharing, rather than the standard convolutional layers. Thus we trained it on the largest facial dataset to-date, an identity labeled dataset of four million facial images belonging to more than 4, 000 identities. The learned representations coupling the accurate model-based alignment with the large facial database generalize remarkably well to faces in unconstrained environments, even with a simple classifier. Our method reaches an accuracy of 97.35% on the Labeled Faces in the Wild (LFW) dataset, reducing the error of the current state of the art by more than 27%, closely approaching human-level performance.Keywords
This publication has 23 references indexed in Scilit:
- Viewing Real-World Faces in 3DPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Deep Convolutional Network Cascade for Facial Point DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Probabilistic Elastic Matching for Pose Variant Face VerificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Volume structured ordinal features with background similarity measure for video face recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Fisher Vector Faces in the WildPublished by British Machine Vision Association and Society for Pattern Recognition ,2013
- Learning hierarchical representations for face verification with convolutional deep belief networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Attribute and simile classifiers for face verificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Unsupervised Joint Alignment of Complex ImagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Learning representations by back-propagating errorsNature, 1986