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 到查詢結果 [ author_sort:"wan, li." ]

切換: 標籤 | MARC模式 | ISBD

Joint Training of a Neural Network a...

Wan, Li.

FindBook

Google Book

Amazon

博客來

Joint Training of a Neural Network and a Structured Model for Computer Vision.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Joint Training of a Neural Network and a Structured Model for Computer Vision./
作者:	Wan, Li.
面頁冊數:	103 p.
附註:	Source: Dissertation Abstracts International, Volume: 76-08(E), Section: B.
Contained By:	Dissertation Abstracts International76-08B(E).
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3685922
ISBN:	9781321624977

Joint Training of a Neural Network and a Structured Model for Computer Vision.
Wan, Li.

Joint Training of a Neural Network and a Structured Model for Computer Vision. - 103 p.

Source: Dissertation Abstracts International, Volume: 76-08(E), Section: B.

Thesis (Ph.D.)--New York University, 2015.

Identifying objects and telling where they are in real world images is one of the most important problems in Artificial Intelligence. The problem is challenging due to: occluded objects, varying object viewpoints and object deformations. This makes the vision problem extremely difficult and cannot be efficiently solved without learning.

ISBN: 9781321624977Subjects--Topical Terms:

523869
Computer science.

Joint Training of a Neural Network and a Structured Model for Computer Vision.
LDR:02785nmm a2200289 4500 001 2066957
005 20160321080102.5
008 170521s2015 ||||||||||||||||| ||eng d
020 $a 9781321624977
035 $a (MiAaPQ)AAI3685922
035 $a AAI3685922
040 $a MiAaPQ $c MiAaPQ
100 1 $a Wan, Li. $3 1034051
245 1 0 $a Joint Training of a Neural Network and a Structured Model for Computer Vision.
300 $a 103 p.
500 $a Source: Dissertation Abstracts International, Volume: 76-08(E), Section: B.
500 $a Adviser: Rob Fergus.
502 $a Thesis (Ph.D.)--New York University, 2015.
520 $a Identifying objects and telling where they are in real world images is one of the most important problems in Artificial Intelligence. The problem is challenging due to: occluded objects, varying object viewpoints and object deformations. This makes the vision problem extremely difficult and cannot be efficiently solved without learning.
520 $a This thesis explores hybrid systems that combine a neural network as a trainable feature extractor and structured models that capture high level information such as object parts. The resulting models combine the strengths of the two approaches: a deep neural network which provides a powerful non-linear feature transformation and a high level structured model which integrates domain-specific knowledge. We develop discriminative training algorithms to jointly optimize these entire models end-to-end.
520 $a First, we proposed a unified model which combines a deep neural network with a latent topic model for image classification. The hybrid model is shown to outperform models based solely on neural networks or topic model alone. Next, we investigate techniques for training a neural network system, introducing an effective way of regularizing the network called DropConnect. DropConnect allows us to train large models while avoiding over-fitting. This yields state-of-the-art results on a variety of standard benchmarks for image classification. Third, we worked on object detection for PASCAL challenge. We improved the deformable parts model and proposed a new non-maximal suppression algorithm. This system was the joint winner of the 2011 challenge. Finally, we develop a new hybrid model which integrates a deep network, deformable parts model and non-maximal suppression. Joint training of our hybrid model shows clear advantage over train each component individually, and achieving competitive result on standard benchmarks.
590 $a School code: 0146.
650 4 $a Computer science. $3 523869
690 $a 0984
710 2 $a New York University. $b Computer Science. $3 1065424
773 0 $t Dissertation Abstracts International $g 76-08B(E).
790 $a 0146
791 $a Ph.D.
792 $a 2015
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3685922