國立虎尾科技大學 |

Towards Learning Representations in Visual Computing Tasks.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Towards Learning Representations in Visual Computing Tasks./
作者:	Chandakkar, Parag Shridhar.
面頁冊數:	1 online resource (183 pages)
附註:	Source: Dissertation Abstracts International, Volume: 79-05(E), Section: B.
標題:	Artificial intelligence. -
電子資源:	click for full text (PQDT)
ISBN:	9780355517002

Towards Learning Representations in Visual Computing Tasks.
Chandakkar, Parag Shridhar.

Towards Learning Representations in Visual Computing Tasks. - 1 online resource (183 pages)

Source: Dissertation Abstracts International, Volume: 79-05(E), Section: B.

Thesis (Ph.D.)--Arizona State University, 2017.

Includes bibliographical references

The performance of most of the visual computing tasks depends on the quality of the features extracted from the raw data. Insightful feature representation increases the performance of many learning algorithms by exposing the underlying explanatory factors of the output for the unobserved input. A good representation should also handle anomalies in the data such as missing samples and noisy input caused by the undesired, external factors of variation. It should also reduce the data redundancy. Over the years, many feature extraction processes have been invented to produce good representations of raw images and videos.

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

Mode of access: World Wide Web

ISBN: 9780355517002Subjects--Topical Terms:

559380
Artificial intelligence.
Index Terms--Genre/Form:

554714
Electronic books.

Towards Learning Representations in Visual Computing Tasks.
LDR:03582ntm a2200349K 4500 001 912183
005 20180608102941.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9780355517002
035 $a (MiAaPQ)AAI10680415
035 $a (MiAaPQ)asu:17485
035 $a AAI10680415
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Chandakkar, Parag Shridhar. $3 1184427
245 1 0 $a Towards Learning Representations in Visual Computing Tasks.
264 0 $c 2017
300 $a 1 online resource (183 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: 79-05(E), Section: B.
500 $a Adviser: Baoxin Li.
502 $a Thesis (Ph.D.)--Arizona State University, 2017.
504 $a Includes bibliographical references
520 $a The performance of most of the visual computing tasks depends on the quality of the features extracted from the raw data. Insightful feature representation increases the performance of many learning algorithms by exposing the underlying explanatory factors of the output for the unobserved input. A good representation should also handle anomalies in the data such as missing samples and noisy input caused by the undesired, external factors of variation. It should also reduce the data redundancy. Over the years, many feature extraction processes have been invented to produce good representations of raw images and videos.
520 $a The feature extraction processes can be categorized into three groups. The first group contains processes that are hand-crafted for a specific task. Hand-engineering features requires the knowledge of domain experts and manual labor. However, the feature extraction process is interpretable and explainable. Next group contains the latent-feature extraction processes. While the original feature lies in a high-dimensional space, the relevant factors for a task often lie on a lower dimensional manifold. The latent-feature extraction employs hidden variables to expose the underlying data properties that cannot be directly measured from the input. Latent features seek a specific structure such as sparsity or low-rank into the derived representation through sophisticated optimization techniques. The last category is that of deep features. These are obtained by passing raw input data with minimal pre-processing through a deep network. Its parameters are computed by iteratively minimizing a task-based loss.
520 $a In this dissertation, I present four pieces of work where I create and learn suitable data representations. The first task employs hand-crafted features to perform clinically-relevant retrieval of diabetic retinopathy images. The second task uses latent features to perform content-adaptive image enhancement. The third task ranks a pair of images based on their aestheticism. The goal of the last task is to capture localized image artifacts in small datasets with patch-level labels. For both these tasks, I propose novel deep architectures and show significant improvement over the previous state-of-art approaches. A suitable combination of feature representations augmented with an appropriate learning approach can increase performance for most visual computing tasks.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Artificial intelligence. $3 559380
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Arizona State University. $b Computer Science. $3 845377
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10680415 $z click for full text (PQDT)