國立虎尾科技大學 |

Correlation alignment for domain adaptation.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Correlation alignment for domain adaptation./
作者:	Sun, Baochen.
面頁冊數:	1 online resource (127 pages)
附註:	Source: Dissertation Abstracts International, Volume: 78-06(E), Section: B.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9781369540383

Correlation alignment for domain adaptation.
Sun, Baochen.

Correlation alignment for domain adaptation. - 1 online resource (127 pages)

Source: Dissertation Abstracts International, Volume: 78-06(E), Section: B.

Thesis (Ph.D.)--University of Massachusetts Lowell, 2016.

Includes bibliographical references

Unlike human learning, machine learning often fails to handle changes between training (source) and test (target) input distributions. Such domain shifts, common in practical scenarios, severely damage the performance of conventional machine learning methods. Supervised domain adaptation methods have been proposed for the case when the target data have labels, including some that perform very well despite being frustratingly easy to implement. However, in practice, the target domain is often unlabeled, requiring unsupervised adaptation.

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

Mode of access: World Wide Web

ISBN: 9781369540383Subjects--Topical Terms:

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

554714
Electronic books.

Correlation alignment for domain adaptation.
LDR:03765ntm a2200361K 4500 001 915316
005 20180727125212.5
006 m o u
007 cr mn||||a|a||
008 190606s2016 xx obm 000 0 eng d
020 $a 9781369540383
035 $a (MiAaPQ)AAI10308095
035 $a AAI10308095
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Sun, Baochen. $3 1188636
245 1 0 $a Correlation alignment for domain adaptation.
264 0 $c 2016
300 $a 1 online resource (127 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: 78-06(E), Section: B.
500 $a Adviser: Kate Saenko.
502 $a Thesis (Ph.D.)--University of Massachusetts Lowell, 2016.
504 $a Includes bibliographical references
520 $a Unlike human learning, machine learning often fails to handle changes between training (source) and test (target) input distributions. Such domain shifts, common in practical scenarios, severely damage the performance of conventional machine learning methods. Supervised domain adaptation methods have been proposed for the case when the target data have labels, including some that perform very well despite being frustratingly easy to implement. However, in practice, the target domain is often unlabeled, requiring unsupervised adaptation.
520 $a This thesis proposes a simple, effective, and efficient method for unsupervised domain adaptation called CORrelation ALignment (CORAL). CORAL minimizes domain shift by aligning the second-order statistics of source and target distributions, without requiring any target labels. It is more general than the subspace manifold methods because it aligns the distributions of the source and target domain rather than the bases. It is also much simpler than other distribution matching methods. CORAL performs remarkably well in extensive evaluations on standard benchmark datasets.
520 $a We also develop novel domain adaptation algorithms by applying the idea of CORAL to three different scenarios. For linear classifiers, we equivalently apply CORAL to the classifier weights, leading to added efficiency when the number of classifiers is small but the number and dimensionality of target examples are very high. The resulting CORAL Linear Discriminant Analysis (CORAL-LDA) outperforms LDA by a large margin on standard domain adaptation benchmarks. The second scenario is applying CORAL to subspace manifold based methods.
520 $a We incorporate the idea of CORAL into two recently published methods and the resulting CORAL-SS method outperforms its counterparts consistently. Last but not least, we extend CORAL to learn a nonlinear transformation that aligns correlations of layer activations in deep neural networks. The resulting Deep CORAL approach works seamlessly with deep networks and achieves state-of-the-art performance on standard benchmark datasets.
520 $a The last part of the thesis explores two new scenarios for visual domain adaptation: from virtual to reality and from ground to sky. In virtual to reality, the source domain contains synthetic images generated from 3D CAD models while the target data are real images. For ground to sky, the target domain includes aerial images while the source data are the common consumer photos. These new scenarios provide much larger shifts and more practical applications to facilitate future research in domain adaptation.
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 University of Massachusetts Lowell. $3 1179049
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10308095 $z click for full text (PQDT)