.png){kind=icon}
返回
Dynamic selection for reconstructing instance-dependent noisy labels
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2024.110803.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
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.
Keyword:
Instance-dependent noise
Label reconstruction
Sample selection
Identity mapping
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
LongReMix: Robust learning with high confidence samples in a noisy label environmentLongReMix: 在嘈杂的标签环境中具有高置信度样本的鲁棒学习.png)
PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏A balanced random learning strategy for CNN based Landsat image segmentation under imbalanced and noisy labelsPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏ScanMix: Learning from Severe Label Noise via Semantic Clustering and Semi-Supervised LearningScanMix: 通过语义聚类和半监督学习从严重的标签噪声中学习PATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Wavelet Transform-based Higher-order Statistics for Fault Diagnosis in Rolling Element Bearings
PREAI
分享收藏On better detecting and leveraging noisy samples for learning with severe label noisePATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
查看更多内容