.png){kind=icon}
返回
Output Regularization With Cluster-Based Soft Targets
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2023.3262267.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
While supervised learning of over-parameterized neural networks achieved state-of-the-art performance in image classification, it tends to over-fit the labeled training samples to give inferior generalization ability. Output regularization deals with over-fitting by using soft targets as additional training signals. Although clustering is one of the most fundamental data analysis tools for discovering general-purpose and data-driven structures, it has been ignored in existing output regularization approaches. In this article, we leverage this underlying structural information by proposing Cluster-based soft targets for Output Regularization (CluOReg). This approach provides a unified way for simultaneous clustering in embedding space and neural classifier training with cluster-based soft targets via output regularization. By explicitly calculating a class relationship matrix in the cluster space, we obtain classwise soft targets shared by all samples in each class. Results of image classification experiments under various settings on a number of benchmark datasets are provided. Without resorting to external models or designed data augmentation, we get consistent and significant reductions in classification error compared with other approaches, demonstrating that cluster-based soft targets effectively complement the ground-truth label.
Keyword:
Training
Predictive models
Neural networks
Task analysis
Supervised learning
Smoothing methods
Representation learning
Clustering
image classification
output regularization
soft label
supervised learning
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
Spectrophotometric Determination of Carbon Disulfide Using Bis(4-(4 -Nitrophenyl)azo-2-Nitrophenyl) Disulfide双 (4-硝基苯基) azo-2-Nitrophenyl) 二硫化物分光光度法测定二硫化碳
.png){kind=icon}
PREAI
分享收藏分享收藏
分享收藏
查看更多内容