Surpassing Human-Level Face Verification Performance on LFW with GaussianFace

04/15/2014
by   Chaochao Lu, et al.
0

Face verification remains a challenging problem in very complex conditions with large variations such as pose, illumination, expression, and occlusions. This problem is exacerbated when we rely unrealistically on a single training data source, which is often insufficient to cover the intrinsically complex face variations. This paper proposes a principled multi-task learning approach based on Discriminative Gaussian Process Latent Variable Model, named GaussianFace, to enrich the diversity of training data. In comparison to existing methods, our model exploits additional data from multiple source-domains to improve the generalization performance of face verification in an unknown target-domain. Importantly, our model can adapt automatically to complex data distributions, and therefore can well capture complex face variations inherent in multiple sources. Extensive experiments demonstrate the effectiveness of the proposed model in learning from diverse data sources and generalize to unseen domain. Specifically, the accuracy of our algorithm achieves an impressive accuracy rate of 98.52 challenging Labeled Faces in the Wild (LFW) benchmark. For the first time, the human-level performance in face verification (97.53

READ FULL TEXT

page 8

page 9

page 10

page 11

research
02/28/2019

FaceLiveNet+: A Holistic Networks For Face Authentication Based On Dynamic Multi-task Convolutional Neural Networks

This paper proposes a holistic multi-task Convolutional Neural Networks ...
research
05/18/2021

Unsupervised Compound Domain Adaptation for Face Anti-Spoofing

We address the problem of face anti-spoofing which aims to make the face...
research
04/19/2016

Triplet Probabilistic Embedding for Face Verification and Clustering

Despite significant progress made over the past twenty five years, uncon...
research
04/25/2018

DisguiseNet : A Contrastive Approach for Disguised Face Verification in the Wild

This paper describes our approach for the Disguised Faces in the Wild (D...
research
01/21/2014

Multi-Directional Multi-Level Dual-Cross Patterns for Robust Face Recognition

To perform unconstrained face recognition robust to variations in illumi...
research
06/27/2012

Deep Lambertian Networks

Visual perception is a challenging problem in part due to illumination v...
research
12/13/2017

Learning Disentangling and Fusing Networks for Face Completion Under Structured Occlusions

Face completion aims to generate semantically new pixels for missing fac...

Please sign up or login with your details

Forgot password? Click here to reset