|
|
|
|
LEADER |
01000naa a22002652 4500 |
001 |
NLM321842707 |
003 |
DE-627 |
005 |
20231225180742.0 |
007 |
cr uuu---uuuuu |
008 |
231225s2022 xx |||||o 00| ||eng c |
024 |
7 |
|
|a 10.1109/TPAMI.2021.3060446
|2 doi
|
028 |
5 |
2 |
|a pubmed24n1072.xml
|
035 |
|
|
|a (DE-627)NLM321842707
|
035 |
|
|
|a (NLM)33625976
|
040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
041 |
|
|
|a eng
|
100 |
1 |
|
|a Wu, Aming
|e verfasserin
|4 aut
|
245 |
1 |
0 |
|a Instance-Invariant Domain Adaptive Object Detection Via Progressive Disentanglement
|
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 Revised 06.07.2022
|
500 |
|
|
|a published: Print-Electronic
|
500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
520 |
|
|
|a Most state-of-the-art methods of object detection suffer from poor generalization ability when the training and test data are from different domains. To address this problem, previous methods mainly explore to align distribution between source and target domains, which may neglect the impact of the domain-specific information existing in the aligned features. Besides, when transferring detection ability across different domains, it is important to extract the instance-level features that are domain-invariant. To this end, we explore to extract instance-invariant features by disentangling the domain-invariant features from the domain-specific features. Particularly, a progressive disentangled mechanism is proposed to decompose domain-invariant and domain-specific features, which consists of a base disentangled layer and a progressive disentangled layer. Then, with the help of Region Proposal Network (RPN), the instance-invariant features are extracted based on the output of the progressive disentangled layer. Finally, to enhance the disentangled ability, we design a detached optimization to train our model in an end-to-end fashion. Experimental results on four domain-shift scenes show our method is separately 2.3, 3.6, 4.0, and 2.0 percent higher than the baseline method. Meanwhile, visualization analysis demonstrates that our model owns well disentangled ability
|
650 |
|
4 |
|a Journal Article
|
700 |
1 |
|
|a Han, Yahong
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Zhu, Linchao
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Yang, Yi
|e verfasserin
|4 aut
|
773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 44(2022), 8 vom: 31. Aug., Seite 4178-4193
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
773 |
1 |
8 |
|g volume:44
|g year:2022
|g number:8
|g day:31
|g month:08
|g pages:4178-4193
|
856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2021.3060446
|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 44
|j 2022
|e 8
|b 31
|c 08
|h 4178-4193
|