國立虎尾科技大學 |

Visual Domain Adaptation in the Deep Learning Era

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Visual Domain Adaptation in the Deep Learning Era/ by Gabriela Csurka, Timothy M. Hospedales, Mathieu Salzmann, Tatiana Tommasi.
作者:	Csurka, Gabriela.
其他作者:	Hospedales, Timothy M.
面頁冊數:	IV, 190 p.online resource. :
Contained By:	Springer Nature eBook
標題:	Computer Vision. -
電子資源:	https://doi.org/10.1007/978-3-031-79175-8
ISBN:	9783031791758

Visual Domain Adaptation in the Deep Learning Era
Csurka, Gabriela.

Visual Domain Adaptation in the Deep Learning Era[electronic resource] /by Gabriela Csurka, Timothy M. Hospedales, Mathieu Salzmann, Tatiana Tommasi. - 1st ed. 2022. - IV, 190 p.online resource. - Synthesis Lectures on Computer Vision,2153-1064. - Synthesis Lectures on Computer Vision,.

Solving problems with deep neural networks typically relies on massive amounts of labeled training data to achieve high performance. While in many situations huge volumes of unlabeled data can be and often are generated and available, the cost of acquiring data labels remains high. Transfer learning (TL), and in particular domain adaptation (DA), has emerged as an effective solution to overcome the burden of annotation, exploiting the unlabeled data available from the target domain together with labeled data or pre-trained models from similar, yet different source domains. The aim of this book is to provide an overview of such DA/TL methods applied to computer vision, a field whose popularity has increased significantly in the last few years. We set the stage by revisiting the theoretical background and some of the historical shallow methods before discussing and comparing different domain adaptation strategies that exploit deep architectures for visual recognition. We introduce the space of self-training-based methods that draw inspiration from the related fields of deep semi-supervised and self-supervised learning in solving the deep domain adaptation. Going beyond the classic domain adaptation problem, we then explore the rich space of problem settings that arise when applying domain adaptation in practice such as partial or open-set DA, where source and target data categories do not fully overlap, continuous DA where the target data comes as a stream, and so on. We next consider the least restrictive setting of domain generalization (DG), as an extreme case where neither labeled nor unlabeled target data are available during training. Finally, we close by considering the emerging area of learning-to-learn and how it can be applied to further improve existing approaches to cross domain learning problems such as DA and DG.

ISBN: 9783031791758

Standard No.: 10.1007/978-3-031-79175-8doiSubjects--Topical Terms:

1127422
Computer Vision.

LC Class. No.: TA1501-1820

Dewey Class. No.: 006

Visual Domain Adaptation in the Deep Learning Era
LDR:03228nam a22003855i 4500 001 1087131
003 DE-He213
005 20220606033201.0
007 cr nn 008mamaa
008 221228s2022 sz | s |||| 0|eng d
020 $a 9783031791758 $9 978-3-031-79175-8
024 7 $a 10.1007/978-3-031-79175-8 $2 doi
035 $a 978-3-031-79175-8
050 4 $a TA1501-1820
050 4 $a TA1634
072 7 $a UYT $2 bicssc
072 7 $a COM016000 $2 bisacsh
072 7 $a UYT $2 thema
082 0 4 $a 006 $2 23
100 1 $a Csurka, Gabriela. $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 931507
245 1 0 $a Visual Domain Adaptation in the Deep Learning Era $h [electronic resource] / $c by Gabriela Csurka, Timothy M. Hospedales, Mathieu Salzmann, Tatiana Tommasi.
250 $a 1st ed. 2022.
264 1 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2022.
300 $a IV, 190 p. $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 Synthesis Lectures on Computer Vision, $x 2153-1064
520 $a Solving problems with deep neural networks typically relies on massive amounts of labeled training data to achieve high performance. While in many situations huge volumes of unlabeled data can be and often are generated and available, the cost of acquiring data labels remains high. Transfer learning (TL), and in particular domain adaptation (DA), has emerged as an effective solution to overcome the burden of annotation, exploiting the unlabeled data available from the target domain together with labeled data or pre-trained models from similar, yet different source domains. The aim of this book is to provide an overview of such DA/TL methods applied to computer vision, a field whose popularity has increased significantly in the last few years. We set the stage by revisiting the theoretical background and some of the historical shallow methods before discussing and comparing different domain adaptation strategies that exploit deep architectures for visual recognition. We introduce the space of self-training-based methods that draw inspiration from the related fields of deep semi-supervised and self-supervised learning in solving the deep domain adaptation. Going beyond the classic domain adaptation problem, we then explore the rich space of problem settings that arise when applying domain adaptation in practice such as partial or open-set DA, where source and target data categories do not fully overlap, continuous DA where the target data comes as a stream, and so on. We next consider the least restrictive setting of domain generalization (DG), as an extreme case where neither labeled nor unlabeled target data are available during training. Finally, we close by considering the emerging area of learning-to-learn and how it can be applied to further improve existing approaches to cross domain learning problems such as DA and DG.
650 2 4 $a Computer Vision. $3 1127422
650 0 $a Image processing—Digital techniques. $3 1365735
650 0 $a Computer vision. $3 561800
650 0 $a Pattern recognition systems. $3 557384
650 1 4 $a Computer Imaging, Vision, Pattern Recognition and Graphics. $3 671334
650 2 4 $a Automated Pattern Recognition. $3 1365734
700 1 $a Hospedales, Timothy M. $e author. $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1394089
700 1 $a Salzmann, Mathieu. $e author. $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1394090
700 1 $a Tommasi, Tatiana. $e author. $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1394091
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer Nature eBook
776 0 8 $i Printed edition: $z 9783031791802
776 0 8 $i Printed edition: $z 9783031791703
776 0 8 $i Printed edition: $z 9783031791857
830 0 $a Synthesis Lectures on Computer Vision, $x 2153-1064 $3 1390325
856 4 0 $u https://doi.org/10.1007/978-3-031-79175-8
912 $a ZDB-2-SXSC
950 $a Synthesis Collection of Technology (R0) (SpringerNature-85007)