|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM360937063 |
| 003 |
DE-627 |
| 005 |
20231226084102.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2023 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2023.3306352
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1203.xml
|
| 035 |
|
|
|a (DE-627)NLM360937063
|
| 035 |
|
|
|a (NLM)37594873
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Wang, Wenjian
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a MMT
|b Cross Domain Few-Shot Learning via Meta-Memory Transfer
|
| 264 |
|
1 |
|c 2023
|
| 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 07.11.2023
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Few-shot learning aims to recognize novel categories solely relying on a few labeled samples, with existing few-shot methods primarily focusing on the categories sampled from the same distribution. Nevertheless, this assumption cannot always be ensured, and the actual domain shift problem significantly reduces the performance of few-shot learning. To remedy this problem, we investigate an interesting and challenging cross-domain few-shot learning task, where the training and testing tasks employ different domains. Specifically, we propose a Meta-Memory scheme to bridge the domain gap between source and target domains, leveraging style-memory and content-memory components. The former stores intra-domain style information from source domain instances and provides a richer feature distribution. The latter stores semantic information through exploration of knowledge of different categories. Under the contrastive learning strategy, our model effectively alleviates the cross-domain problem in few-shot learning. Extensive experiments demonstrate that our proposed method achieves state-of-the-art performance on cross-domain few-shot semantic segmentation tasks on the COCO-20 i, PASCAL-5 i, FSS-1000, and SUIM datasets and positively affects few-shot classification tasks on Meta-Dataset
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Duan, Lijuan
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Wang, Yuxi
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Fan, Junsong
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhang, Zhaoxiang
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 45(2023), 12 vom: 18. Dez., Seite 15018-15035
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:45
|g year:2023
|g number:12
|g day:18
|g month:12
|g pages:15018-15035
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2023.3306352
|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 45
|j 2023
|e 12
|b 18
|c 12
|h 15018-15035
|