|
|
|
|
| LEADER |
01000naa a22002652c 4500 |
| 001 |
NLM388631376 |
| 003 |
DE-627 |
| 005 |
20250714100855.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
250714s2025 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2025.3569196
|2 doi
|
| 028 |
5 |
2 |
|a pubmed25n1410.xml
|
| 035 |
|
|
|a (DE-627)NLM388631376
|
| 035 |
|
|
|a (NLM)40378021
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Jing, Kunlei
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Recursive Confidence Training for Pseudo-Labeling Calibration in Semi-Supervised Few-Shot Learning
|
| 264 |
|
1 |
|c 2025
|
| 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 19.05.2025
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status Publisher
|
| 520 |
|
|
|a Semi-Supervised Few-Shot Learning (SSFSL) aims to address the data scarcity in few-shot learning by leveraging both a few labeled support data and abundant unlabeled data. In SSFSL, a classifier trained on scarce support data is often biased and thus assigns inaccurate pseudo-labels to the unlabeled data, which will mislead downstream learning tasks. To combat this issue, we introduce a novel method called Certainty-Aware Recursive Confidence Training (CARCT). CARCT hinges on the insight that selecting pseudo-labeled data based on confidence levels can yield more informative support data, which is crucial for retraining an unbiased classifier to achieve accurate pseudo-labeling-a process we term pseudo-labeling calibration. We observe that accurate pseudo-labels typically exhibit smaller certainty entropy, indicating high-confidence pseudo-labeling compared to those of inaccurate pseudo-labels. Accordingly, CARCT constructs a joint double-Gaussian model to fit the certainty entropies collected across numerous SSFSL tasks. Thereby, A semi-supervised Prior Confidence Distribution (ssPCD) is learned to aid in distinguishing between high-confidence and low-confidence pseudo-labels. During an SSFSL task, ssPCD guides the selection of both high-confidence and low-confidence pseudo-labeled data to retrain the classifier that then assigns more accurate pseudo-labels to the low-confidence pseudo-labeled data. Such recursive confidence training continues until the low-confidence ones are exhausted, terminating the pseudo-labeling calibration. The unlabeled data all receive accurate pseudo-labels to expand the few support data to generalize the downstream learning task, which in return meta-refines the classifier, named self-training, to boost the pseudo-labeling in subsequent tasks. Extensive experiments on basic and extended SSFSL setups showcase the superiority of CARCT versus state-of-the-art methods, and comprehensive ablation studies and visualizations justify our insight. The source code is available at https://github.com/Klein-JING/CARCT
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Ma, Hebo
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhang, Chen
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Wen, Lei
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhang, Zhaorui
|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 PP(2025) vom: 16. Mai
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnas
|
| 773 |
1 |
8 |
|g volume:PP
|g year:2025
|g day:16
|g month:05
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2025.3569196
|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 PP
|j 2025
|b 16
|c 05
|