國立虎尾科技大學 |

Synthetic Data for Deep Learning

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Synthetic Data for Deep Learning/ by Sergey I. Nikolenko.
作者:	Nikolenko, Sergey I.
面頁冊數:	XII, 348 p. 125 illus., 100 illus. in color.online resource. :
Contained By:	Springer Nature eBook
標題:	Image Processing and Computer Vision. -
電子資源:	https://doi.org/10.1007/978-3-030-75178-4
ISBN:	9783030751784

Synthetic Data for Deep Learning
Nikolenko, Sergey I.

Synthetic Data for Deep Learning[electronic resource] /by Sergey I. Nikolenko. - 1st ed. 2021. - XII, 348 p. 125 illus., 100 illus. in color.online resource. - Springer Optimization and Its Applications,1741931-6828 ;. - Springer Optimization and Its Applications,104.

1. Introduction -- 2. Synthetic data for basic computer vision problems -- 3. Synthetic simulated environments -- 4. Synthetic data outside computer vision -- 5. Directions in synthetic data development -- 6. Synthetic-to-real domain adaptation and refinement -- 7. Privacy guarantees in synthetic data -- 8. Promising directions for future work -- Conclusion -- References.

This is the first book on synthetic data for deep learning, and its breadth of coverage may render this book as the default reference on synthetic data for years to come. The book can also serve as an introduction to several other important subfields of machine learning that are seldom touched upon in other books. Machine learning as a discipline would not be possible without the inner workings of optimization at hand. The book includes the necessary sinews of optimization though the crux of the discussion centers on the increasingly popular tool for training deep learning models, namely synthetic data. It is expected that the field of synthetic data will undergo exponential growth in the near future. This book serves as a comprehensive survey of the field. In the simplest case, synthetic data refers to computer-generated graphics used to train computer vision models. There are many more facets of synthetic data to consider. In the section on basic computer vision, the book discusses fundamental computer vision problems, both low-level (e.g., optical flow estimation) and high-level (e.g., object detection and semantic segmentation), synthetic environments and datasets for outdoor and urban scenes (autonomous driving), indoor scenes (indoor navigation), aerial navigation, and simulation environments for robotics. Additionally, it touches upon applications of synthetic data outside computer vision (in neural programming, bioinformatics, NLP, and more). It also surveys the work on improving synthetic data development and alternative ways to produce it such as GANs. The book introduces and reviews several different approaches to synthetic data in various domains of machine learning, most notably the following fields: domain adaptation for making synthetic data more realistic and/or adapting the models to be trained on synthetic data and differential privacy for generating synthetic data with privacy guarantees. This discussion is accompanied by an introduction into generative adversarial networks (GAN) and an introduction to differential privacy.

ISBN: 9783030751784

Standard No.: 10.1007/978-3-030-75178-4doiSubjects--Topical Terms:

670819
Image Processing and Computer Vision.

LC Class. No.: Q325.5-.7

Dewey Class. No.: 006.31

Synthetic Data for Deep Learning
LDR:03886nam a22004215i 4500 001 1056288
003 DE-He213
005 20210707132743.0
007 cr nn 008mamaa
008 220103s2021 gw | s |||| 0|eng d
020 $a 9783030751784 $9 978-3-030-75178-4
024 7 $a 10.1007/978-3-030-75178-4 $2 doi
035 $a 978-3-030-75178-4
050 4 $a Q325.5-.7
050 4 $a TK7882.P3
072 7 $a UYQM $2 bicssc
072 7 $a COM004000 $2 bisacsh
072 7 $a UYQM $2 thema
082 0 4 $a 006.31 $2 23
100 1 $a Nikolenko, Sergey I. $e author. $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1361618
245 1 0 $a Synthetic Data for Deep Learning $h [electronic resource] / $c by Sergey I. Nikolenko.
250 $a 1st ed. 2021.
264 1 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2021.
300 $a XII, 348 p. 125 illus., 100 illus. in color. $b online resource.
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
347 $a text file $b PDF $2 rda
490 1 $a Springer Optimization and Its Applications, $x 1931-6828 ; $v 174
505 0 $a 1. Introduction -- 2. Synthetic data for basic computer vision problems -- 3. Synthetic simulated environments -- 4. Synthetic data outside computer vision -- 5. Directions in synthetic data development -- 6. Synthetic-to-real domain adaptation and refinement -- 7. Privacy guarantees in synthetic data -- 8. Promising directions for future work -- Conclusion -- References.
520 $a This is the first book on synthetic data for deep learning, and its breadth of coverage may render this book as the default reference on synthetic data for years to come. The book can also serve as an introduction to several other important subfields of machine learning that are seldom touched upon in other books. Machine learning as a discipline would not be possible without the inner workings of optimization at hand. The book includes the necessary sinews of optimization though the crux of the discussion centers on the increasingly popular tool for training deep learning models, namely synthetic data. It is expected that the field of synthetic data will undergo exponential growth in the near future. This book serves as a comprehensive survey of the field. In the simplest case, synthetic data refers to computer-generated graphics used to train computer vision models. There are many more facets of synthetic data to consider. In the section on basic computer vision, the book discusses fundamental computer vision problems, both low-level (e.g., optical flow estimation) and high-level (e.g., object detection and semantic segmentation), synthetic environments and datasets for outdoor and urban scenes (autonomous driving), indoor scenes (indoor navigation), aerial navigation, and simulation environments for robotics. Additionally, it touches upon applications of synthetic data outside computer vision (in neural programming, bioinformatics, NLP, and more). It also surveys the work on improving synthetic data development and alternative ways to produce it such as GANs. The book introduces and reviews several different approaches to synthetic data in various domains of machine learning, most notably the following fields: domain adaptation for making synthetic data more realistic and/or adapting the models to be trained on synthetic data and differential privacy for generating synthetic data with privacy guarantees. This discussion is accompanied by an introduction into generative adversarial networks (GAN) and an introduction to differential privacy.
650 2 4 $a Image Processing and Computer Vision. $3 670819
650 2 4 $a Operations Research, Management Science. $3 785065
650 1 4 $a Machine Learning. $3 1137723
650 0 $a Optical data processing. $3 639187
650 0 $a Management science. $3 719678
650 0 $a Operations research. $3 573517
650 0 $a Machine learning. $3 561253
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer Nature eBook
776 0 8 $i Printed edition: $z 9783030751777
776 0 8 $i Printed edition: $z 9783030751791
776 0 8 $i Printed edition: $z 9783030751807
830 0 $a Springer Optimization and Its Applications, $x 1931-6828 ; $v 104 $3 1255232
856 4 0 $u https://doi.org/10.1007/978-3-030-75178-4
912 $a ZDB-2-SCS
912 $a ZDB-2-SXCS
950 $a Computer Science (SpringerNature-11645)
950 $a Computer Science (R0) (SpringerNature-43710)