Learning Imbalanced Datasets with Maximum Margin Loss

Abstract

A learning algorithm referred to as Maximum Margin (MM) is proposed for considering the class-imbalance data learning issue: the trained model tends to predict the majority of classes rather than the minority ones. That is, underfitting for minority classes seems to be one of the challenges of generalization. For a good generalization of the minority classes, we design a new Maximum Margin (MM) loss function, motivated by minimizing a margin-based generalization bound through the shifting decision bound. The theoretically-principled label-distribution-aware margin (LDAM) loss was successfully applied with prior strategies such as re-weighting or re-sampling along with the effective training schedule. However, they did not investigate the maximum margin loss function yet. In this study, we investigate the performances of two types of hard maximum margin-based decision boundary shift with LDAM's training schedule on artificially imbalanced CIFAR-10/100 for fair comparisons and effectiveness.

References in corpus (8)

• A systematic study of the class imbalance problem in convolutional neural networks
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• Additive Margin Softmax for Face Verification
• Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting
• Rethinking the Value of Labels for Improving Class-Imbalanced Learning
• The Devil is in the Tails: Fine-grained Classification in the Wild
• What is the Effect of Importance Weighting in Deep Learning?
• Maximum margin learning of t-SPNs for cell classification with filtered input

Cited by in corpus (2)

• Skew Class-balanced Re-weighting for Unbiased Scene Graph Generation
• CardioCaps: Attention-based Capsule Network for Class-Imbalanced Echocardiogram Classification