|
|
|
|
| LEADER |
01000caa a22002652c 4500 |
| 001 |
NLM373453019 |
| 003 |
DE-627 |
| 005 |
20250306071140.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
240611s2024 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2024.3409024
|2 doi
|
| 028 |
5 |
2 |
|a pubmed25n1244.xml
|
| 035 |
|
|
|a (DE-627)NLM373453019
|
| 035 |
|
|
|a (NLM)38857136
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Li, Haochen
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a REACT
|b Remainder Adaptive Compensation for Domain Adaptive Object Detection
|
| 264 |
|
1 |
|c 2024
|
| 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 14.06.2024
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Domain adaptive object detection (DAOD) aims to infer a robust detector on the target domain with the labelled source datasets. Recent studies utilize a feature extractor shared on the source and target domains to capture the domain-invariant features and the task-relevant information with both feature-alignment constraint and source annotations. However, the feature extractor shared across domains discards partial task-relevant information of the target domain due to the domain gap and lack of target annotations, leading to compromised discrimination capabilities within target domain. To this end, we propose a novel REmainder Adaptive CompensaTion network (REACT) to adaptively compensate the extracted features with the remainder features for generating task-relevant features. The key insight is that the remainder features contain the discarded task-relevant information, so they can be adapted to compensate for the inadequate target features. Especially, REACT introduces an additional remainder branch to regain the remainder features, and then adaptively utilizes them to compensate for the discarded task-relevant information, improving discrimination on the target domain. Extensive experiments over multiple cross-domain adaptation tasks with three baselines demonstrate that our approach gains significant improvements and achieves superior performance compared with highly-optimized state-of-the-art methods
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Zhang, Rui
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yao, Hantao
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhang, Xin
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Hao, Yifan
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Song, Xinkai
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Li, Ling
|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 33(2024) vom: 10., Seite 3735-3748
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnas
|
| 773 |
1 |
8 |
|g volume:33
|g year:2024
|g day:10
|g pages:3735-3748
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2024.3409024
|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 33
|j 2024
|b 10
|h 3735-3748
|