國立虎尾科技大學 |

Learning-Based Approaches for Pixel-Level Prediction.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Learning-Based Approaches for Pixel-Level Prediction./
作者:	Baig, Mohammad Haris.
面頁冊數:	1 online resource (141 pages)
附註:	Source: Dissertation Abstracts International, Volume: 79-04(E), Section: B.
Contained By:	Dissertation Abstracts International79-04B(E).
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9780355394689

Learning-Based Approaches for Pixel-Level Prediction.
Baig, Mohammad Haris.

Learning-Based Approaches for Pixel-Level Prediction. - 1 online resource (141 pages)

Source: Dissertation Abstracts International, Volume: 79-04(E), Section: B.

Thesis (Ph.D.)

Includes bibliographical references

Images are a rich source of information about our physical world. A fundamental limitation in developing interactive applications that leverage image data has been getting machines to understand what the stream of numbers composing images represents. We study the design of learning-based approaches for understanding images at a pixel level. Our work focuses on addressing the following questions: 1) What representation is most useful for pixel-level reasoning, and how can we obtain these features from image data? 2) How can we design and train deep models for problems where each pixel can have multiple correct interpretations? 3) How can we exploit spatial coherence within adjacent image regions to assist with reasoning about content at the pixel level?

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

Mode of access: World Wide Web

ISBN: 9780355394689Subjects--Topical Terms:

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

554714
Electronic books.

Learning-Based Approaches for Pixel-Level Prediction.
LDR:03500ntm a2200397Ki 4500 001 910834
005 20180517112611.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9780355394689
035 $a (MiAaPQ)AAI10624046
035 $a (MiAaPQ)dartmouth:11252
035 $a AAI10624046
040 $a MiAaPQ $b eng $c MiAaPQ
099 $a TUL $f hyy $c available through World Wide Web
100 1 $a Baig, Mohammad Haris. $3 1182312
245 1 0 $a Learning-Based Approaches for Pixel-Level Prediction.
264 0 $c 2017
300 $a 1 online resource (141 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: 79-04(E), Section: B.
500 $a Adviser: Lorenzo Torresani.
502 $a Thesis (Ph.D.) $c Dartmouth College $d 2017.
504 $a Includes bibliographical references
520 $a Images are a rich source of information about our physical world. A fundamental limitation in developing interactive applications that leverage image data has been getting machines to understand what the stream of numbers composing images represents. We study the design of learning-based approaches for understanding images at a pixel level. Our work focuses on addressing the following questions: 1) What representation is most useful for pixel-level reasoning, and how can we obtain these features from image data? 2) How can we design and train deep models for problems where each pixel can have multiple correct interpretations? 3) How can we exploit spatial coherence within adjacent image regions to assist with reasoning about content at the pixel level?
520 $a We show that designing pixel-level descriptors by incorporating image-level information (in addition to information from the local neighborhood of a pixel) leads to significant improvements in our ability to estimate depth from a single image.
520 $a As it is challenging to learn such pixel-level representations due to a lack of labeled training data, we also study approaches for learning pixel-level representations in unsupervised settings, e.g., colorizing grayscale images and image inpainting.
520 $a We propose an architecture targeted at improving the ability of models to predict pixel-level data when there are multiple correct outputs possible for each pixel. We show how to train our proposed architecture to allow for diversity within the output hypothesis space.
520 $a Finally, we explore image inpainting as a mechanism for exploiting spatial coherence for improving the performance of patch-based image compression models. Our study reveals that there is a need to design new architectural components for extracting pixel-level information for performing inpainting. We also show that compression performance improves the most when the inpainting model is trained jointly (for an inpainting and compression objective) with a modified learning objective, allowing our model not only to learn how to inpaint effectively but also to discover what to inpaint for bringing about the greatest improvement in compression.
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
650 4 $a Artificial intelligence. $3 559380
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Dartmouth College. $b Computer Science. $3 1182313
773 0 $t Dissertation Abstracts International $g 79-04B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10624046 $z click for full text (PQDT)