|
|
|
|
| LEADER |
01000caa a22002652 4500 |
| 001 |
NLM367901773 |
| 003 |
DE-627 |
| 005 |
20240606232337.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
240202s2024 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2024.3360623
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1430.xml
|
| 035 |
|
|
|a (DE-627)NLM367901773
|
| 035 |
|
|
|a (NLM)38300782
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Wu, Songhua
|e verfasserin
|4 aut
|
| 245 |
1 |
2 |
|a A Time-Consistency Curriculum for Learning From Instance-Dependent Noisy Labels
|
| 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 06.06.2024
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Many machine learning algorithms are known to be fragile on simple instance-independent noisy labels. However, noisy labels in real-world data are more devastating since they are produced by more complicated mechanisms in an instance-dependent manner. In this paper, we target this practical challenge of Instance-Dependent Noisy Labels by jointly training (1) a model reversely engineering the noise generating mechanism, which produces an instance-dependent mapping between the clean label posterior and the observed noisy label and (2) a robust classifier that produces clean label posteriors. Compared to previous methods, the former model is novel and enables end-to-end learning of the latter directly from noisy labels. An extensive empirical study indicates that the time-consistency of data is critical to the success of training both models and motivates us to develop a curriculum selecting training data based on their dynamics on the two models' outputs over the course of training. We show that the curriculum-selected data provide both clean labels and high-quality input-output pairs for training the two models. Therefore, it leads to promising and robust classification performance even in notably challenging settings of instance-dependent noisy labels where many SoTA methods could easily fail. Extensive experimental comparisons and ablation studies further demonstrate the advantages and significance of the time-consistency curriculum in learning from instance-dependent noisy labels on multiple benchmark datasets
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Zhou, Tianyi
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Du, Yuxuan
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yu, Jun
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Han, Bo
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Liu, Tongliang
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 46(2024), 7 vom: 03. Juni, Seite 4830-4842
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:46
|g year:2024
|g number:7
|g day:03
|g month:06
|g pages:4830-4842
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2024.3360623
|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 46
|j 2024
|e 7
|b 03
|c 06
|h 4830-4842
|