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% on the well-known and challenging Labeled Faces in the Wild (LFW) benchmark. For the first time, the human-level performance in face verification (97.53%) on LFW is surpassed.

There is an implicit belief among many psychologists and computer scientists that human face verification abilities are currently beyond existing computer-based face verification algorithms [39]. This belief, however, is supported more by anecdotal impression than by scientific evidence. By contrast, there have already been a number of papers comparing human and computer-based face verification performance [2, 54, 40, 41, 38, 8]. It has been shown that the best current face verification algorithms perform better than humans in the good and moderate conditions. So, it is really not that difficult to beat human performance in some specific scenarios.

9. Conclusion and Future Work

This paper presents a principled Multi-Task Learning approach based on Discriminative Gaussian Process Latent Variable Model, named GaussianFace, for face verification by including a computationally more efficient equivalent form of KFDA and the multi-task learning constraint to the DGPLVM model. We use Gaussian Processes approximation and anchor graphs to speed up the inference and prediction of our model. Based on the GaussianFace model, we propose two different approaches for face verification. Extensive experiments on challenging datasets validate the efficacy of our model. The GaussianFace model finally surpassed human-level face verification accuracy, thanks to exploiting additional data from multiple source-domains to improve the generalization performance of face verification in the target-domain and adapting automatically to complex face variations. Although several techniques such as the Laplace approximation and anchor graph are introduced to speed up the process of inference and prediction in our GaussianFace model, it still takes a long time to train our model for the high performance. In addition, large memory is also necessary. Therefore, for specific application, one needs to balance the three dimensions: memory, running time, and performance. Generally speaking, higher performance requires more memory and more running time. In the future, the issue of running time can be further addressed by the distributed parallel algorithm or the GPU implementation of large matrix inversion. To address the issue of memory, some online algorithms for training need to be developed. Another more intuitive method is to seek a more efficient sparse representation for the large covariance matrix.

Surpassing Human-Level Face Verification Performance on LFW with GaussianFace的更多相关文章

  1. 人脸识别算法准确率最终超过了人类 The Face Recognition Algorithm That Finally Outperforms Humans

    Everybody has had the experience of not recognising someone they know—changes in pose, illumination ...

  2. [C5] Andrew Ng - Structuring Machine Learning Projects

    About this Course You will learn how to build a successful machine learning project. If you aspire t ...

  3. System and method for dynamically adjusting to CPU performance changes

    FIELD OF THE INVENTION The present invention is related to computing systems, and more particularly ...

  4. cvpr2015papers

    @http://www-cs-faculty.stanford.edu/people/karpathy/cvpr2015papers/ CVPR 2015 papers (in nicer forma ...

  5. deeplearning.ai 卷积神经网络 Week 4 特殊应用:人脸识别和神经风格转换 听课笔记

    本周课程的主题是两大应用:人脸检测和风格迁移. 1. Face verification vs. face recognition Verification: 一对一的问题. 1) 输入:image, ...

  6. Rolling in the Deep (Learning)

    Rolling in the Deep (Learning) Deep Learning has been getting a lot of press lately, and is one of t ...

  7. linux tcp调优

    Linux TCP Performance Tuning News Linux Performance Tuning Recommended Books Recommended Links Linux ...

  8. (转) Deep Reinforcement Learning: Pong from Pixels

    Andrej Karpathy blog About Hacker's guide to Neural Networks Deep Reinforcement Learning: Pong from ...

  9. AndrewNG Deep learning课程笔记

    神经网络基础 Deep learning就是深层神经网络 神经网络的结构如下, 这是两层神经网络,输入层一般不算在内,分别是hidden layer和output layer hidden layer ...

随机推荐

  1. 2017.5.15 markdown简明教程

    0.说明 markdown是一种书写格式,html是一种发布格式.markdown的语法种类只对应html标记的一小部分(只涵盖纯文本). 不在markdown涵盖范围的标签,都可以直接在文档里用ht ...

  2. OpenSSL 有关密钥的那些事儿(HOWTO keys)

    <DRAFT!> OpenSSL 有关密钥的那些事儿(HOWTO keys) 1. 介绍(Introduction) Keys are the basis of public key al ...

  3. Android Crash 定位

    本文介绍了如何在 Android 手机发生 Crash 时进行 Log 分析的方法, 它可以帮助测试人员快速定位 Android 手机 Crash 发生的原因,同时给研发人员提供有效修改 Bug 的 ...

  4. Windows服务器SYSTEM权限Webshell无法添加3389账户情况突破总结

    转自:http://bbs.blackbap.org/thread-2331-1-1.html 近好多Silic的朋友在Windows下SYSTEM权限的php webshell下添加账户,但是却无法 ...

  5. xtrabackup详解

    xtrabackup是Percona公司CTO Vadim参与开发的一款基于InnoDB的在线热备工具,具有开源,免费,支持在线热备,备份恢复速度快,占用磁盘空间小等特点,并且支持不同情况下的多种备份 ...

  6. 从程序员到asp.net架构师转变[转]

    微软的DotNet开发绝对是属于那种入门容易提高难的技术.而要能够成为DotNet架构师没有三年或更长时间的编码积累基本上是不可能的.特别是在大型软件项目中,架构师是项目核心成员,承上启下,因此 RU ...

  7. shell3

    例一:监控httpd是否正常运行并自动开启 #!/bin/bash port=$(nmap -sT localhost | grep 'http$' |awk '{print $2}') riqi=$ ...

  8. 2015级C++第7周项目 友元、共享数据保护、多文件结构

    [项目1-成员函数.友元函数和一般函数有差别]參考解答 (1)阅读以下的程序,体会凝视中的说明(要执行程序,请找到课程主页并复制代码) //例:使用成员函数.友元函数和一般函数的差别 #include ...

  9. 【BIEE】04_当维度表中的维不存在事实表中,需要展示所有维度并且数据类展示为0

    有时候,我们往往会存在这样的需求 例如:事实表的数据如下 EMP_FACT表示事实表,DIM_LEVEL是维度表 预期效果:(根据员工信息,分析各等级员工工资与员工个数) 我们在BIEE报表中新建报表 ...

  10. 【VBA】获取Excle的安装路径

    在VBA中,如何获取Excle的安装路径呢?请看以下代码: Sub 获取Excle的安装路径() MsgBox "Excle的安装路径为:" & Application.P ...