DeepFace: Closing the Gap to Human-Level Performance in Face Verification

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.

PDF Abstract Conference on 2014 PDF Conference on 2014 Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Face Verification Labeled Faces in the Wild DeepFace Accuracy 98.37% # 5
3D Face Modelling LFW DeepFace 1-of-100 Accuracy 70 # 1

Methods


No methods listed for this paper. Add relevant methods here