|
|
|
|
| LEADER |
01000caa a22002652 4500 |
| 001 |
NLM366444751 |
| 003 |
DE-627 |
| 005 |
20240405233329.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
240108s2024 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2023.3347850
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1366.xml
|
| 035 |
|
|
|a (DE-627)NLM366444751
|
| 035 |
|
|
|a (NLM)38153827
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Xia, Xiaobo
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Regularly Truncated M-Estimators for Learning With 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 05.04.2024
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a The sample selection approach is very popular in learning with noisy labels. As deep networks "learn pattern first", prior methods built on sample selection share a similar training procedure: the small-loss examples can be regarded as clean examples and used for helping generalization, while the large-loss examples are treated as mislabeled ones and excluded from network parameter updates. However, such a procedure is arguably debatable from two folds: (a) it does not consider the bad influence of noisy labels in selected small-loss examples; (b) it does not make good use of the discarded large-loss examples, which may be clean or have meaningful information for generalization. In this paper, we propose regularly truncated M-estimators (RTME) to address the above two issues simultaneously. Specifically, RTME can alternately switch modes between truncated M-estimators and original M-estimators. The former can adaptively select small-losses examples without knowing the noise rate and reduce the side-effects of noisy labels in them. The latter makes the possibly clean examples but with large losses involved to help generalization. Theoretically, we demonstrate that our strategies are label-noise-tolerant. Empirically, comprehensive experimental results show that our method can outperform multiple baselines and is robust to broad noise types and levels
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Lu, Pengqian
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Gong, Chen
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Han, Bo
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yu, Jun
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yu, Jun
|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), 5 vom: 25. Apr., Seite 3522-3536
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:46
|g year:2024
|g number:5
|g day:25
|g month:04
|g pages:3522-3536
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2023.3347850
|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 5
|b 25
|c 04
|h 3522-3536
|