東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Representation Learning and Image Sy...

Yin, Xi.

FindBook

Google Book

Amazon

博客來

Representation Learning and Image Synthesis for Deep Face Recognition.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Representation Learning and Image Synthesis for Deep Face Recognition./
作者:	Yin, Xi.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2018,
面頁冊數:	124 p.
附註:	Source: Dissertation Abstracts International, Volume: 79-12(E), Section: B.
Contained By:	Dissertation Abstracts International79-12B(E).
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10930064
ISBN:	9780438289192

Representation Learning and Image Synthesis for Deep Face Recognition.
Yin, Xi.

Representation Learning and Image Synthesis for Deep Face Recognition. - Ann Arbor : ProQuest Dissertations & Theses, 2018 - 124 p.

Source: Dissertation Abstracts International, Volume: 79-12(E), Section: B.

Thesis (Ph.D.)--Michigan State University, 2018.

Face recognition has been advanced a lot in recent years thanks to the development of deep neural networks. The large intra-class variations in pose, illumination, and expression are the long-standing challenges. Learning a discriminative representation that is robust to these variations is the key. In the scenarios of profile pose or long-tail training data, image or feature-level data augmentation is needed. This dissertation presents three different methods to solve these problems. First, we explore a multi-task Convolutional Neural Network (CNN) that aims to leverage side tasks to improve representation learning. A pose-directed multi-task CNN is introduced to better handle pose variation. The proposed framework is effective in pose-invariant face recognition. Second, we propose a Face Frontalization-Generative Adversarial Network (FF-GAN) that can generate a frontal face even from an input image with extreme profile pose. FF-GAN handles pose variation from the perspective of image-level data augmentation. Multiple loss functions are proposed to achieve large-pose face frontalization. The proposed approach is evaluated on various tasks including face reconstruction, landmark detection, face frontalization, and face recognition. Third, a feature transfer learning method is presented to solve the problem of insufficient intra-class variation via feature-level data augmentation. A Gaussian prior is assumed across all the regular classes and the variance are transferred from regular classes to long-tail classes. Further, an alternating training regimen is proposed to simultaneously achieve less biased decision boundaries and more discriminative representations. Extensive experiments have demonstrated the effectiveness of the proposed feature transfer framework.

ISBN: 9780438289192Subjects--Topical Terms:

523869
Computer science.

Representation Learning and Image Synthesis for Deep Face Recognition.
LDR:02792nmm a2200313 4500 001 2163917
005 20181114145237.5
008 190424s2018 ||||||||||||||||| ||eng d
020 $a 9780438289192
035 $a (MiAaPQ)AAI10930064
035 $a (MiAaPQ)grad.msu:16300
035 $a AAI10930064
040 $a MiAaPQ $c MiAaPQ
100 1 $a Yin, Xi. $3 1277812
245 1 0 $a Representation Learning and Image Synthesis for Deep Face Recognition.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2018
300 $a 124 p.
500 $a Source: Dissertation Abstracts International, Volume: 79-12(E), Section: B.
500 $a Includes supplementary digital materials.
500 $a Adviser: Xiaoming Liu.
502 $a Thesis (Ph.D.)--Michigan State University, 2018.
520 $a Face recognition has been advanced a lot in recent years thanks to the development of deep neural networks. The large intra-class variations in pose, illumination, and expression are the long-standing challenges. Learning a discriminative representation that is robust to these variations is the key. In the scenarios of profile pose or long-tail training data, image or feature-level data augmentation is needed. This dissertation presents three different methods to solve these problems. First, we explore a multi-task Convolutional Neural Network (CNN) that aims to leverage side tasks to improve representation learning. A pose-directed multi-task CNN is introduced to better handle pose variation. The proposed framework is effective in pose-invariant face recognition. Second, we propose a Face Frontalization-Generative Adversarial Network (FF-GAN) that can generate a frontal face even from an input image with extreme profile pose. FF-GAN handles pose variation from the perspective of image-level data augmentation. Multiple loss functions are proposed to achieve large-pose face frontalization. The proposed approach is evaluated on various tasks including face reconstruction, landmark detection, face frontalization, and face recognition. Third, a feature transfer learning method is presented to solve the problem of insufficient intra-class variation via feature-level data augmentation. A Gaussian prior is assumed across all the regular classes and the variance are transferred from regular classes to long-tail classes. Further, an alternating training regimen is proposed to simultaneously achieve less biased decision boundaries and more discriminative representations. Extensive experiments have demonstrated the effectiveness of the proposed feature transfer framework.
590 $a School code: 0128.
650 4 $a Computer science. $3 523869
650 4 $a Artificial intelligence. $3 516317
690 $a 0984
690 $a 0800
710 2 $a Michigan State University. $b Computer Science. $3 1680297
773 0 $t Dissertation Abstracts International $g 79-12B(E).
790 $a 0128
791 $a Ph.D.
792 $a 2018
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10930064