mlsanityData to 14 Oct 2026

Dynamic Curriculum Learning for Imbalanced Data Classification

arXiv 1901.06783 ↗First posted 21 Jan 2019cs.CVcited by 93

Not on the map. Why?

Abstract (arXiv)

Human attribute analysis is a challenging task in the field of computer vision, since the data is largely imbalance-distributed. Common techniques such as re-sampling and cost-sensitive learning require prior-knowledge to train the system. To address this problem, we propose a unified framework called Dynamic Curriculum Learning (DCL) to online adaptively adjust the sampling strategy and loss learning in single batch, which resulting in better generalization and discrimination. Inspired by the curriculum learning, DCL consists of two level curriculum schedulers: (1) sampling scheduler not only manages the data distribution from imbalanced to balanced but also from easy to hard; (2) loss scheduler controls the learning importance between classification and metric learning loss. Learning from these two schedulers, we demonstrate our DCL framework with the new state-of-the-art performance on the widely used face attribute dataset CelebA and pedestrian attribute dataset RAP.

Key facts. Cited by 93 papers in the map (data through 14 Oct 2026). First posted on arXiv 21 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 20; 2022: 23; 2023: 8; 2024: 17; 2025: 13; 2026: 12.

93 papers.

Sort:

By area:

  1. 2021Deep Long-Tailed Learning: A Surveycited by 417
  2. 2021Curriculum Learning: A Surveycited by 259
  3. 2021CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learningcited by 175
  4. 2021Distributional Robustness Loss for Long-tail Learningcited by 84
  5. 2022Competence-based Multimodal Curriculum Learning for Medical Report Generationcited by 76
  6. 2022A Survey on Long-Tailed Visual Recognitioncited by 75
  7. 2023Towards Accurate Post-Training Quantization for Vision Transformercited by 71
  8. 2021Diversifying Sample Generation for Accurate Data-Free Quantizationcited by 63
  9. 2021Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learningcited by 53
  10. 2022Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentationcited by 33
  11. 2021Robust Attentive Deep Neural Network for Exposing GAN-generated Facescited by 28
  12. 2021Distribution-sensitive Information Retention for Accurate Binary Neural Networkcited by 25
38 more
  1. 2024Swift Sampler: Efficient Learning of Sampler by 10 Parameterscited by 25
  2. 2021Procrustean Training for Imbalanced Deep Learningcited by 24
  3. 2023Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusioncited by 24
  4. 2022Delving into Semantic Scale Imbalancecited by 22
  5. 2021Gradual Domain Adaptation in the Wild:When Intermediate Distributions are Absentcited by 21
  6. 2022Graph Neural Network with Curriculum Learning for Imbalanced Node Classificationcited by 19
  7. 2022PIDray: A Large-scale X-ray Benchmark for Real-World Prohibited Item Detectioncited by 17
  8. 2022Weakly-supervised Temporal Path Representation Learning with Contrastive Curriculum Learning -- Extended Versioncited by 15
  9. 2023Curriculum Graph Machine Learning: A Surveycited by 15
  10. 2024Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognitioncited by 15
  11. 2025Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classificationcited by 14
  12. 2022Paraphrase Identification with Deep Learning: A Review of Datasets and Methodscited by 13
  13. 2021Learning to Predict Trustworthiness with Steep Slope Losscited by 11
  14. 2024A Survey of Deep Long-Tail Classification Advancementscited by 11
  15. 2021Hierarchical Knowledge Guided Learning for Real-world Retinal Diseases Recognitioncited by 10
  16. 2024Geometric Prior Guided Feature Representation Learning for Long-Tailed Classificationcited by 10
  17. 2025A Comprehensive Survey on Imbalanced Data Learningcited by 10
  18. 2021Improving Facial Attribute Recognition by Group and Graph Learningcited by 7
  19. 2022Towards Federated Long-Tailed Learningcited by 7
  20. 2022G2NetPL: Generic Game-Theoretic Network for Partial-Label Image Classificationcited by 7
  21. 2022Less is More: Adaptive Curriculum Learning for Thyroid Nodule Diagnosiscited by 6
  22. 2023Paced-Curriculum Distillation with Prediction and Label Uncertainty for Image Segmentationcited by 6
  23. 2021Tackling the Imbalance for GNNscited by 5
  24. 2022CRISP: Curriculum based Sequential Neural Decoders for Polar Code Familycited by 5
  25. 2022A Survey of Dataset Refinement for Problems in Computer Vision Datasetscited by 5
  26. 2023Robust Positive-Unlabeled Learning via Noise Negative Sample Self-correctioncited by 5
  27. 2024AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge Distillationcited by 5
  28. 2021Self-Distribution Binary Neural Networkscited by 4
  29. 2022Exploring the Learning Difficulty of Data Theory and Measurecited by 4
  30. 2022Queried Unlabeled Data Improves and Robustifies Class-Incremental Learningcited by 4
  31. 2024A Quality-Centric Framework for Generic Deepfake Detectioncited by 4
  32. 2025Enhancing Vietnamese VQA through Curriculum Learning on Raw and Augmented Text Representationscited by 4
  33. 2021AutoSampling: Search for Effective Data Sampling Schedulescited by 3
  34. 2021Medical Knowledge-Guided Deep Curriculum Learning for Elbow Fracture Diagnosis from X-Ray Imagescited by 3
  35. 2022Detecting, Tracking and Counting Motorcycle Rider Traffic Violations on Unconstrained Roadscited by 3
  36. 2022Cross-Modal Similarity-Based Curriculum Learning for Image Captioningcited by 3
  37. 2024Extracting Clean and Balanced Subset for Noisy Long-tailed Classificationcited by 3
  38. 2024From Easy to Hard: Learning Curricular Shape-aware Features for Robust Panoptic Scene Graph Generationcited by 3

50 most cited of 93 All 93 (JSON)