|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM334877407 |
| 003 |
DE-627 |
| 005 |
20231225224635.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231225s2022 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2021.3136615
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1116.xml
|
| 035 |
|
|
|a (DE-627)NLM334877407
|
| 035 |
|
|
|a (NLM)34951843
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Dai, Pingyang
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Disentangling Task-Oriented Representations for Unsupervised Domain Adaptation
|
| 264 |
|
1 |
|c 2022
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Completed 13.01.2022
|
| 500 |
|
|
|a Date Revised 13.01.2022
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Unsupervised domain adaptation (UDA) aims to address the domain-shift problem between a labeled source domain and an unlabeled target domain. Many efforts have been made to eliminate the mismatch between the distributions of training and testing data by learning domain-invariant representations. However, the learned representations are usually not task-oriented, i.e., being class-discriminative and domain-transferable simultaneously. This drawback limits the flexibility of UDA in complicated open-set tasks where no labels are shared between domains. In this paper, we break the concept of task-orientation into task-relevance and task-irrelevance, and propose a dynamic task-oriented disentangling network (DTDN) to learn disentangled representations in an end-to-end fashion for UDA. The dynamic disentangling network effectively disentangles data representations into two components: the task-relevant ones embedding critical information associated with the task across domains, and the task-irrelevant ones with the remaining non-transferable or disturbing information. These two components are regularized by a group of task-specific objective functions across domains. Such regularization explicitly encourages disentangling and avoids the use of generative models or decoders. Experiments in complicated, open-set scenarios (retrieval tasks) and empirical benchmarks (classification tasks) demonstrate that the proposed method captures rich disentangled information and achieves superior performance
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Chen, Peixian
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Wu, Qiong
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Hong, Xiaopeng
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Ye, Qixiang
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Tian, Qi
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Lin, Chia-Wen
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Ji, Rongrong
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|d 1992
|g 31(2022) vom: 24., Seite 1012-1026
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnns
|
| 773 |
1 |
8 |
|g volume:31
|g year:2022
|g day:24
|g pages:1012-1026
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2021.3136615
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 31
|j 2022
|b 24
|h 1012-1026
|