论文标题
分阶段的渐进学习与耦合 - 调节失衡损失的数据分类不平衡
Phased Progressive Learning with Coupling-Regulation-Imbalance Loss for Imbalanced Data Classification
论文作者
论文摘要
当面对遇到数量失衡和分类困难的数据集时，深度卷积神经网络的表现通常很差。尽管该领域的进步，但现有的两阶段方法仍表现出数据集偏差或域移位。为了解决这个问题，已经提出了一个分阶段的渐进学习时间表，该时间表逐渐将重点从表示学习转变为培训上层分类器。这种方法对于较大失衡或样本较少的数据集特别有益。另一种新方法提出了耦合 - 调节失衡损失函数，结合了三个部分：校正项，局灶性损失和LDAM损失。这种损失可有效解决数量不平衡和异常值，同时调节对分类困难的样本的关注重点。这些方法在几个基准数据集上产生了令人满意的结果，包括不平衡的CIFAR10，不平衡的CIFAR100，Imagenet-LT和Inaturalist 2018，并且可以轻松地将其推广到其他不平衡的分类模型。
Deep convolutional neural networks often perform poorly when faced with datasets that suffer from quantity imbalances and classification difficulties. Despite advances in the field, existing two-stage approaches still exhibit dataset bias or domain shift. To counter this, a phased progressive learning schedule has been proposed that gradually shifts the emphasis from representation learning to training the upper classifier. This approach is particularly beneficial for datasets with larger imbalances or fewer samples. Another new method a coupling-regulation-imbalance loss function is proposed, which combines three parts: a correction term, Focal loss, and LDAM loss. This loss is effective in addressing quantity imbalances and outliers, while regulating the focus of attention on samples with varying classification difficulties. These approaches have yielded satisfactory results on several benchmark datasets, including Imbalanced CIFAR10, Imbalanced CIFAR100, ImageNet-LT, and iNaturalist 2018, and can be easily generalized to other imbalanced classification models.
