國立虎尾科技大學 |

Visual Representations for Fine-grained Categorization.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Visual Representations for Fine-grained Categorization./
Author:	Zhang, Ning.
Description:	1 online resource (83 pages)
Notes:	Source: Dissertation Abstracts International, Volume: 77-08(E), Section: B.
Subject:	Computer science. -
Online resource:	click for full text (PQDT)
ISBN:	9781339593029

Visual Representations for Fine-grained Categorization.
Zhang, Ning.

Visual Representations for Fine-grained Categorization. - 1 online resource (83 pages)

Source: Dissertation Abstracts International, Volume: 77-08(E), Section: B.

Thesis (Ph.D.)--University of California, Berkeley, 2015.

Includes bibliographical references

In contrast to basic-level object recognition, fine-grained categorization aims to distinguish between subordinate categories, such as different animal breeds or species, plant species or man-made product models. The problem can be extremely challenging due to the subtle differences in the appearance of certain parts across related categories and often requires distinctions that must be conditioned on the object pose for reliable identification. Discriminative markings are often highly localized, leading traditional object recognition approaches to struggle with the large pose variations often present in these domains. Face recognition is the classic case of fine-grained recognition, and it is noteworthy that the best face recognition methods jointly discover facial landmarks and extract features from those locations. We propose pose-normalized representations, which align training exemplars, either piecewise by part or globally for the whole object, effectively factoring out differences in pose and in camera viewing angle.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9781339593029Subjects--Topical Terms:

573171
Computer science.
Index Terms--Genre/Form:

554714
Electronic books.

Visual Representations for Fine-grained Categorization.
LDR:03069ntm a2200325K 4500 001 913627
005 20180622095234.5
006 m o u
007 cr mn||||a|a||
008 190606s2015 xx obm 000 0 eng d
020 $a 9781339593029
035 $a (MiAaPQ)AAI10086169
035 $a (MiAaPQ)berkeley:15842
035 $a AAI10086169
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Zhang, Ning. $3 1023566
245 1 0 $a Visual Representations for Fine-grained Categorization.
264 0 $c 2015
300 $a 1 online resource (83 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 77-08(E), Section: B.
500 $a Adviser: Trevor Darrell.
502 $a Thesis (Ph.D.)--University of California, Berkeley, 2015.
504 $a Includes bibliographical references
520 $a In contrast to basic-level object recognition, fine-grained categorization aims to distinguish between subordinate categories, such as different animal breeds or species, plant species or man-made product models. The problem can be extremely challenging due to the subtle differences in the appearance of certain parts across related categories and often requires distinctions that must be conditioned on the object pose for reliable identification. Discriminative markings are often highly localized, leading traditional object recognition approaches to struggle with the large pose variations often present in these domains. Face recognition is the classic case of fine-grained recognition, and it is noteworthy that the best face recognition methods jointly discover facial landmarks and extract features from those locations. We propose pose-normalized representations, which align training exemplars, either piecewise by part or globally for the whole object, effectively factoring out differences in pose and in camera viewing angle.
520 $a I first present the methods of using the idea of pose-normalization for two related applications: human attribute classification and person recognition beyond frontal face. Following the recent success of deep learning, we use deep convolutional features as feature representations. Next, I will introduce the part-based RCNN method as an extension of state-of-art object detection method RCNN for fine-grained categorization. The model learns both whole-object and part detectors, and enforces learned geometric constraints between them. I will also show the results of using the recent compact bilinear features to generate the pose-normalized representations. However, bottom-up region proposals is limited by hand-engineered features and in the final work, I will present a fully convolution deep network, trained end-to-end for part localization and fine-grained classification.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of California, Berkeley. $b Computer Science. $3 1179511
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10086169 $z click for full text (PQDT)