arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.05298cs.CV
收藏

分类的类内不确定性损失函数

Intra-Class Uncertainty Loss Function for Classification

Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);CAS Center for Excellence in Brain Science and Intelligence Technology(中国科学院脑科学与智能技术卓越创新中心);School of Future Technology, University of Chinese Academy of Sciences(中国科学院大学未来技术学院)

He Zhu, Shan Yu

摘要:

大多数分类模型可以看作是模板匹配的过程。然而,当不考虑类内不确定性/可变性时,特别是对于包含不平衡类的数据集,这可能导致分类错误。为了解决这个问题,我们提出了一个损失函数与类内不确定性高斯分布。具体来说,在我们的框架中,每个类别的深度网络提取的特征都具有独立的高斯分布特征。分布的参数与其他网络参数一起使用似然正则化来学习。高斯的均值在现有方法中扮演类似于中心锚的角色,方差描述了不同类别的不确定性。此外,与传统损失函数中的类间间隔相似,我们引入了类内不确定性的间隔,使得每个类更加紧凑,减少了不同类别特征分布的不平衡。基于MNIST,CIFAR,ImageNet和Long-tailed CIFAR分析,所提出的方法通过学习更好的类表示来提高分类性能。

英文摘要:

Most classification models can be considered as the process of matching templates. However, when intra-class uncertainty/variability is not considered, especially for datasets containing unbalanced classes, this may lead to classification errors. To address this issue, we propose a loss function with intra-class uncertainty following Gaussian distribution. Specifically, in our framework, the features extracted by deep networks of each class are characterized by independent Gaussian distribution. The parameters of distribution are learned with a likelihood regularization along with other network parameters. The means of the Gaussian play a similar role as the center anchor in existing methods, and the variance describes the uncertainty of different classes. In addition, similar to the inter-class margin in traditional loss functions, we introduce a margin to intra-class uncertainty to make each cluster more compact and reduce the imbalance of feature distribution from different categories. Based on MNIST, CIFAR, ImageNet, and Long-tailed CIFAR analyses, the proposed approach shows improved classification performance, through learning a better class representation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑