mlsanityData to 14 Oct 2026

Learning Imbalanced Datasets with Maximum Margin Loss

arXiv 2206.05380 ↗First posted 11 Jun 2022cs.LG cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 18 of its 24 references that are in the map. First posted on arXiv 11 Jun 2022.

Builds on

18 of 24 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
  4. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,492
  5. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
  6. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  7. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 809
  8. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 737
  9. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 705
  10. 2017A systematic study of the class imbalance problem in convolutional neural networkscited by 513
  11. 2017Scene Graph Generation by Iterative Message Passingcited by 462
  12. 2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
6 more
  1. 2016Large-Margin Softmax Loss for Convolutional Neural Networkscited by 296
  2. 2018Additive Margin Softmax for Face Verificationcited by 278
  3. 2018What is the Effect of Importance Weighting in Deep Learning?cited by 251
  4. 2020Rethinking the Value of Labels for Improving Class-Imbalanced Learningcited by 216
  5. 2017The Devil is in the Tails: Fine-grained Classification in the Wildcited by 89
  6. 2019Striking the Right Balance with Uncertaintycited by 79

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 3; 2025: 1; 2026: 2.

9 papers.

  1. 2023Class-Balancing Diffusion Modelscited by 48
  2. 2023Skew Class-balanced Re-weighting for Unbiased Scene Graph Generationcited by 5
  3. 2023Enlarged Large Margin Loss for Imbalanced Classificationcited by 2
  4. 2024Optimizing for ROC Curves on Class-Imbalanced Data by Training over a Family of Loss Functionscited by 0
  5. 2024CardioCaps: Attention-based Capsule Network for Class-Imbalanced Echocardiogram Classificationcited by 0
  6. 2024Training Over a Distribution of Hyperparameters for Enhanced Performance and Adaptability on Imbalanced Classificationcited by 0
  7. 2025Long-Tailed Data Classification by Increasing and Decreasing Neurons During Trainingcited by 0
  8. 2026GAS: Enhancing Reward-Cost Balance of Generative Model-assisted Offline Safe RLcited by 0
  9. 2026ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margincited by 0