.png){kind=icon}
返回
Group benefits instance for data purification
.png){kind=icon}
PRE
AI
DOI：10.1016/j.compeleceng.2024.109156.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Manually annotating datasets for training deep models is very labor-intensive and timeconsuming. To overcome such inferiority, directly leveraging web images to conduct training data becomes a natural choice. Nevertheless, the presence of label noise in web data usually degrades the model performance. Existing methods for combating label noise are typically designed and tested on synthetic noisy datasets. However, they tend to fail to achieve satisfying results on real -world noisy datasets. To this end, we propose a method named GRIP to alleviate the noisy label problem for both synthetic and real -world datasets. Specifically, GRIP utilizes a group regularization strategy that estimates class soft labels to improve noise -robustness. Soft label supervision reduces overfitting on noisy labels and learns inter -class similarities to benefit classification. Furthermore, an instance purification operation globally identifies noisy labels by measuring the difference between each training sample and its class soft label. Through operations at both group and instance levels, our approach integrates the advantages of noiserobust and noise -cleaning methods and remarkably alleviates the performance degradation caused by noisy labels. Comprehensive experimental results on synthetic and real -world datasets demonstrate the superiority of GRIP over the existing state-of-the-art methods. The data and source code of this work have been made available at: https://github.com/NUST-MachineIntelligence-Laboratory/GRIP.
Keyword:
Label noise
Noise-robust
Noise-cleaning
Data purification
期刊
C
IF:
4.9
论文数:
6.7K
被引数:
1.3W
机构
引用论文
Adaptive top-hat filter based on quantum genetic algorithm for infrared small target detection基于量子遗传算法的自适应顶帽滤波红外小目标检测
PREAI
分享收藏
分享收藏Advances in Data Preprocessing for Biomedical Data Fusion: An Overview of the Methods, Challenges, and Prospects.png)
INFORMATION FUSION
OAAI
INFORMATION FUSIONIF15.5
OAAI分享收藏Lead stimulates Golgi sialyltransferase at times coincident with the embryonic to adult conversion of the neural cell adhesion molecule (N-CAM)Toxicology
ToxicologyIF0
PREAI
分享收藏
查看更多内容