Surpassing Human-Level Face Verification Performance on LFW with GaussianFace
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
- 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 ...
- [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 ...
- 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 ...
- cvpr2015papers
@http://www-cs-faculty.stanford.edu/people/karpathy/cvpr2015papers/ CVPR 2015 papers (in nicer forma ...
- 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, ...
- 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 ...
- linux tcp调优
Linux TCP Performance Tuning News Linux Performance Tuning Recommended Books Recommended Links Linux ...
- (转) Deep Reinforcement Learning: Pong from Pixels
Andrej Karpathy blog About Hacker's guide to Neural Networks Deep Reinforcement Learning: Pong from ...
- 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
- [转]解决Docker容器时间与主机不一致问题
原文: https://blog.csdn.net/luckystar689/article/details/76572046 https://stackoverflow.com/questions/ ...
- 2017.8.5 VMware的介绍与安装
1 VMware简介 官网地址:http://www.vmware.com VMware的功能: 是一个虚拟PC的软件,可以在现有的操作系统上虚拟出一个新的硬件环境,相当于模拟出一台新的PC,以此来实 ...
- Node.js 网页瘸腿稍强点爬虫再体验
这回爬虫走得好点了,每次正常读取文章数目总是一样的,但是有程序僵住了情况,不知什么原因. 代码如下: // 内置http模块,提供了http服务器和客户端功能 var http=require(&qu ...
- Sublime Text 3 文档
中文版:http://feliving.github.io/Sublime-Text-3-Documentation/ 英文版:http://www.sublimetext.com/docs/3/
- 底部菜单实现(Dialog方案)
项目中经常会要实现在屏幕底部弹出一个窗口,比如一个分享窗口: 下面详解实现步骤: 1.定义布局 <?xml version="1.0" encoding="utf- ...
- STL源代码剖析 容器 stl_list.h
本文为senlie原创.转载请保留此地址:http://blog.csdn.net/zhengsenlie list ----------------------------------------- ...
- react-native AsyncStorage 数据持久化方案
1,AsyncStorage介绍 AsyncStorage 是一个简单的.异步的.持久化的 Key-Value 存储系统,它对于 App 来说是全局性的.它用来代替 LocalStorage. 由于它 ...
- SQL中拆分字符串substr及统计字符出现频数replace用法实例讲解
一.拆分字符串为若干行 例一:要求将表emp中的'king'按照每行一个单词拆成四行 注意:substr(str,pos):截取pos位置开始的字符: substr(str,pos,len):从pos ...
- vs无法引用项目问题
vs无法引用项目问题 2017年12月13日 14:45:31 阅读数:582 开发时编译报错--项目A未被引用,展开项目的引用,发现该项目实质已经被引用了,但是该引用上有个黄色三角感叹号,遂移除该引 ...
- 读书报告之《改动代码的艺术》 (I)
<改动代码的艺术>,英文名<Working Effectively with Legacy Code>,中文翻译的文笔上绝对谈不上"艺术"二字.愧对艺术二字 ...