|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM356299848 |
| 003 |
DE-627 |
| 005 |
20231226070152.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2023 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2023.3271451
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1187.xml
|
| 035 |
|
|
|a (DE-627)NLM356299848
|
| 035 |
|
|
|a (NLM)37126626
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Shu, Jun
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a CMW-Net
|b Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning
|
| 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 06.09.2023
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Modern deep neural networks can easily overfit to biased training data containing corrupted labels or class imbalance. Sample re-weighting methods are popularly used to alleviate this data bias issue. Most current methods, however, require to manually pre-specify the weighting schemes relying on the characteristics of the investigated problem and training data. This makes them fairly hard to be generally applied in practical scenarios, due to their significant complexities and inter-class variations of data bias. To address this issue, we propose a meta-model capable of adaptively learning an explicit weighting scheme directly from data. Specifically, by seeing each training class as a separate learning task, our method aims to extract an explicit weighting function with sample loss and task/class feature as input, and sample weight as output, expecting to impose adaptively varying weighting schemes to different sample classes based on their own intrinsic bias characteristics. Extensive experiments substantiate the capability of our method on achieving proper weighting schemes in various data bias cases, like class imbalance, feature-independent and dependent label noises, and more complicated bias scenarios beyond conventional cases. Besides, the task-transferability of the learned weighting scheme is also substantiated, by readily deploying the weighting function learned on relatively smaller-scale CIFAR-10 dataset on much larger-scale full WebVision dataset. The general availability of our method for multiple robust deep learning issues, including partial-label learning, semi-supervised learning and selective classification, has also been validated. Code for reproducing our experiments is available at https://github.com/xjtushujun/CMW-Net
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Yuan, Xiang
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Meng, Deyu
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Xu, Zongben
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 45(2023), 10 vom: 01. Okt., Seite 11521-11539
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:45
|g year:2023
|g number:10
|g day:01
|g month:10
|g pages:11521-11539
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2023.3271451
|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 10
|b 01
|c 10
|h 11521-11539
|