.png){kind=icon}
返回
Learning sample representativeness for class-imbalanced multi-label classification
.png){kind=icon}
PRE
AI
DOI：10.1007/s10044-024-01209-8.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Class imbalance is a common problem that often occurs in multi-label image classification. In multi-label datasets, the co-occurrence of labels presents a unique set of difficulties, making it hard for traditional methods to produce satisfactory results, particularly on tail classes. Based on previous research and our investigation, we have found that the number of labels presents in a given sample can influence classification results. Nevertheless, it is worth noting that certain samples within the tail classes exhibit resistance to this influence, which is a critical aspect in the context of class-imbalanced multi-label classification. In this paper, we term these samples as representative samples. Highlighting representative samples during training can effectively address the above issues. Specifically, we propose a new method to learn sample representativeness, which is named Representativeness-Emphasizing Loss (REL). First, we use a new re-weighting form to rebalance the weights based on sample representativeness. Then, a modified focal loss dynamically assigns tailored parameters for each class in each sample to further emphasize the sample representativeness. Extensive experiments on two class-imbalanced datasets show that models trained with this new loss function achieve comparable performance to existing methods.
Keyword:
Multi-label classification
Class imbalance
Re-weighting representative samples
期刊
IF:
2
论文数:
1.9K
被引数:
1.9K
机构
引用论文
A systematic study of the class imbalance problem in convolutional neural networks卷积神经网络中类不平衡问题的系统研究.png)
NEURAL NETWORKS
OAAI
NEURAL NETWORKSIF6.3
OAAI分享收藏Enhanced deep-joint segmentation with deep learning networks of glioma tumor for multi-grade classification using MR images基于神经胶质瘤深度学习网络的增强深度联合分割，用于MR图像的多级分类
PREAI
分享收藏分享收藏
查看更多内容