mlsanityData to 7 Oct 2026

Influence-Balanced Loss for Imbalanced Visual Classification

arXiv 2110.02444 ↗First posted 6 Oct 2021cs.CV cs.LGcited by 91

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a balancing training method to address problems in imbalanced data learning. To this end, we derive a new loss used in the balancing training phase that alleviates the influence of samples that cause an overfitted decision boundary. The proposed loss efficiently improves the performance of any type of imbalance learning methods. In experiments on multiple benchmark data sets, we demonstrate the validity of our method and reveal that the proposed loss outperforms the state-of-the-art cost-sensitive loss methods. Furthermore, since our loss is not restricted to a specific task, model, or training method, it can be easily used in combination with other recent re-sampling, meta-learning, and cost-sensitive learning methods for class-imbalance problems.

Key facts. Cited by 91 papers in the map (data through 7 Oct 2026). Builds on 15 of its 36 references that are in the map. First posted on arXiv 6 Oct 2021.

Builds on

15 of 36 references.

References · 15

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  4. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
  5. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
  6. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
  7. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  8. 2017A Closer Look at Memorization in Deep Networkscited by 936
  9. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
  10. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 604
  11. 2017A systematic study of the class imbalance problem in convolutional neural networkscited by 510
  12. 2020Balanced Meta-Softmax for Long-Tailed Visual Recognitioncited by 397
3 more
  1. 2019Generative Adversarial Minority Oversamplingcited by 72
  2. 2017Class Rectification Hard Mining for Imbalanced Deep Learningcited by 67
  3. 2020MESA: Boost Ensemble Imbalanced Learning with MEta-SAmplercited by 25

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 14; 2023: 30; 2024: 20; 2025: 16; 2026: 8.

91 papers.

Sort:

By area:

  1. 2021Deep Long-Tailed Learning: A Surveycited by 416
  2. 2021The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classificationcited by 100
  3. 2022Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Studycited by 45
  4. 2024Gradient Reweighting: Towards Imbalanced Class-Incremental Learningcited by 37
  5. 2022Learning Imbalanced Data with Vision Transformerscited by 34
  6. 2022SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learningcited by 30
  7. 2023CUDA: Curriculum of Data Augmentation for Long-Tailed Recognitioncited by 30
  8. 2022Escaping Saddle Points for Effective Generalization on Class-Imbalanced Datacited by 28
  9. 2024A Systematic Review on Long-Tailed Learningcited by 27
  10. 2023Balancing Logit Variation for Long-tailed Semantic Segmentationcited by 26
  11. 2023Subclass-balancing Contrastive Learning for Long-tailed Recognitioncited by 26
  12. 2024Training Unbiased Diffusion Models From Biased Datasetcited by 25
38 more
  1. 2023A Unified Perspective for Loss-Oriented Imbalanced Learning via Localizationcited by 24
  2. 2022OpenTAL: Towards Open Set Temporal Action Localizationcited by 23
  3. 2022Learning to Re-weight Examples with Optimal Transport for Imbalanced Classificationcited by 23
  4. 2023Use Your Head: Improving Long-Tail Video Recognitioncited by 22
  5. 2023Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavationcited by 22
  6. 2023Regularizing Second-Order Influences for Continual Learningcited by 21
  7. 2023Feature Fusion from Head to Tail for Long-Tailed Visual Recognitioncited by 20
  8. 2022Long-tailed Food Classificationcited by 19
  9. 2022Label-Noise Learning with Intrinsically Long-Tailed Datacited by 17
  10. 2021Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Imagescited by 16
  11. 2023Balanced Energy Regularization Loss for Out-of-distribution Detectioncited by 16
  12. 2023Distributionally Robust Post-hoc Classifiers under Prior Shiftscited by 16
  13. 2024Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognitioncited by 15
  14. 2024Multi-level Personalized Federated Learning on Heterogeneous and Long-Tailed Datacited by 14
  15. 2023Single-Stage Heavy-Tailed Food Classificationcited by 10
  16. 2025A Comprehensive Survey on Imbalanced Data Learningcited by 10
  17. 2023SuperDisco: Super-Class Discovery Improves Visual Recognition for the Long-Tailcited by 9
  18. 2023Robust Asymmetric Loss for Multi-Label Long-Tailed Learningcited by 8
  19. 2023RAHNet: Retrieval Augmented Hybrid Network for Long-tailed Graph Classificationcited by 7
  20. 2024Double-Bounded Optimal Transport for Advanced Clustering and Classificationcited by 6
  21. 2024Improving Multi-label Recognition using Class Co-Occurrence Probabilitiescited by 6
  22. 2022Convolutional Fine-Grained Classification with Self-Supervised Target Relation Regularizationcited by 5
  23. 2022A Survey of Dataset Refinement for Problems in Computer Vision Datasetscited by 5
  24. 2022Compound Batch Normalization for Long-tailed Image Classificationcited by 5
  25. 2023Revisiting Long-tailed Image Classification: Survey and Benchmarks with New Evaluation Metricscited by 5
  26. 2023Fairness Improves Learning from Noisily Labeled Long-Tailed Datacited by 5
  27. 2023Personalized Federated Learning on Long-Tailed Data via Adversarial Feature Augmentationcited by 5
  28. 2024Shap-Mix: Shapley Value Guided Mixing for Long-Tailed Skeleton Based Action Recognitioncited by 5
  29. 2023Diffusion Model with Clustering-based Conditioning for Food Image Generationcited by 4
  30. 2023Frequency-Aware Self-Supervised Long-Tailed Learningcited by 4
  31. 2023Class Uncertainty: A Measure to Mitigate Class Imbalancecited by 4
  32. 2023Generalized Categories Discovery for Long-tailed Recognitioncited by 4
  33. 2024AnchorAL: Computationally Efficient Active Learning for Large and Imbalanced Datasetscited by 4
  34. 2024Clip Body and Tail Separately: High Probability Guarantees for DPSGD with Heavy Tailscited by 4
  35. 2022ImDrug: A Benchmark for Deep Imbalanced Learning in AI-aided Drug Discoverycited by 3
  36. 2022Minority-Oriented Vicinity Expansion with Attentive Aggregation for Video Long-Tailed Recognitioncited by 3
  37. 2023LIVABLE: Exploring Long-Tailed Classification of Software Vulnerability Typescited by 3
  38. 2023ImbaGCD: Imbalanced Generalized Category Discoverycited by 3

50 most cited of 91 All 91 (JSON)