.png){kind=icon}
Return
Dynamic selection for reconstructing instance-dependent noisy labels
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2024.110803.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
As an inevitable issue in annotating large-scale datasets, instance-dependent label noise (IDN) can cause serious overfitting in neural networks. To combat IDN, label reconstruction methods have been developed with noise transition matrices or DNNs to simulate the transition from clean labels to noisy labels. Nevertheless, the absence of correct supervisions will lead to learning wrong noise transitions. This motivates us to select samples with clean labels to fetch the correct supervisions. However, the difficulty in obtaining prior knowledge of the noise rate prohibits the use of existing sample selection methods. To this end, we propose a dynamic sample selection method, namely Identity Mapping (IdMap), to overcome this limitation. Inspired by the feature-dependent characteristic of IDN, we first introduce the extracted instance features and pseudo-ground- truth labels to reconstruct noisy labels. A partial identity mapping between two labels is then established and samples with consistent identity mapping output are selected as clean data to update the classifier. Extensive experiments on both artificial and real-world noisy datasets demonstrate the superiority of IdMap compared with other state-of-the-art methods.
Keywords:
Instance-dependent noise
Label reconstruction
Sample selection
Identity mapping
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
Cited Papers
LongReMix: Robust learning with high confidence samples in a noisy label environment.png)
PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAIShareSaveA balanced random learning strategy for CNN based Landsat image segmentation under imbalanced and noisy labelsPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveScanMix: Learning from Severe Label Noise via Semantic Clustering and Semi-Supervised LearningPATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAIShareSaveWavelet Transform-based Higher-order Statistics for Fault Diagnosis in Rolling Element Bearings
PREAI
ShareSaveOn better detecting and leveraging noisy samples for learning with severe label noisePATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSave
ShareSave
View more