摘要
传统分类算法一般要求数据集类别分布平衡,然而在实际情况中往往面临的是不平衡的类别分布。目前存在的数据层面和模型层面算法试图从不同角度解决该问题,但面临着参数选择以及重复采样产生的额外计算等问题。针对此问题,提出了一种在小批量内样本损失自适应均衡化的方法。该算法采用了一种动态学习损失函数的方式,根据小批量内样本标签信息调整各样本损失权重,从而实现在小批量内各类别样本总损失的平衡性。通过在caltech101和ILSVRC2014数据集上的实验表明,该算法能够有效地减少计算成本并提高分类精度,且一定程度上避免了过采样方法所带来的模型过拟合风险。
The traditional classification algorithms generally require a balanced distribution of various categories in datasets.However,the traditional classification algorithms often encounter an imbalanced class distribution in real life.The existing data-and classifier-level methods that attempt to solve this problem based on different perspectives exhibit some disadvantages,including the selection of parameters that have to be handled carefully and additional computing power because of repeated sampling.To solve these disadvantages,a method that can adaptively maintain the loss balance of examples in a mini-batch is proposed.This algorithm uses a dynamic loss-learnt function to adjust the loss ratio of each sample based on the information present in the label in every mini-batch,thereby achieving a balanced total loss for each class.The experiments conducted using the caltech101 and ILSVRC2014 datasets denote that this algorithm can effectively reduce the computational cost,improve the classification accuracy,and avoid the overfitting risk of the model that can be attributed to the oversampling method.
作者
黄庆康
宋恺涛
陆建峰
HUANG Qingkang;SONG Kaitao;LU Jianfeng(School of Computer Science and Engineering,Nanjing University of Science and Technology,Nanjing 210094,China)
出处
《智能系统学报》
CSCD
北大核心
2019年第5期953-958,共6页
CAAI Transactions on Intelligent Systems
关键词
不平衡学习
不平衡数据分类
多分类不平衡
损失平衡
不平衡数据分类算法
不平衡数据集
F1调和平均
卷积神经网络
深度学习
imbalanced learning
imbalanced data classification
imbalanced multi-classification
loss balance
classificationalgorithm for imbalanced data
imbalanced dataset
F1 measure
convolutional neural networks
deep learning
