# Dynamic Curriculum Learning for Imbalanced Data Classification

arXiv: https://arxiv.org/abs/1901.06783 · HTML: https://mlsanity.com/paper/1901.06783/

## Key facts

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

## Built on by (most cited first, 30 of 93)

- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [Curriculum Learning: A Survey](https://mlsanity.com/paper/2101.10382/) (2021)
- [CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2102.09559/) (2021)
- [Distributional Robustness Loss for Long-tail Learning](https://mlsanity.com/paper/2104.03066/) (2021)
- [Competence-based Multimodal Curriculum Learning for Medical Report Generation](https://mlsanity.com/paper/2206.14579/) (2022)
- [A Survey on Long-Tailed Visual Recognition](https://mlsanity.com/paper/2205.13775/) (2022)
- [Towards Accurate Post-Training Quantization for Vision Transformer](https://mlsanity.com/paper/2303.14341/) (2023)
- [Diversifying Sample Generation for Accurate Data-Free Quantization](https://mlsanity.com/paper/2103.01049/) (2021)
- [Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learning](https://mlsanity.com/paper/2110.08394/) (2021)
- [Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.10026/) (2022)
- [Robust Attentive Deep Neural Network for Exposing GAN-generated Faces](https://mlsanity.com/paper/2109.02167/) (2021)
- [Distribution-sensitive Information Retention for Accurate Binary Neural Network](https://mlsanity.com/paper/2109.12338/) (2021)
- [Swift Sampler: Efficient Learning of Sampler by 10 Parameters](https://mlsanity.com/paper/2410.05578/) (2024)
- [Procrustean Training for Imbalanced Deep Learning](https://mlsanity.com/paper/2104.01769/) (2021)
- [Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion](https://mlsanity.com/paper/2312.10692/) (2023)
- [Delving into Semantic Scale Imbalance](https://mlsanity.com/paper/2212.14613/) (2022)
- [Gradual Domain Adaptation in the Wild:When Intermediate Distributions are Absent](https://mlsanity.com/paper/2106.06080/) (2021)
- [Graph Neural Network with Curriculum Learning for Imbalanced Node Classification](https://mlsanity.com/paper/2202.02529/) (2022)
- [PIDray: A Large-scale X-ray Benchmark for Real-World Prohibited Item Detection](https://mlsanity.com/paper/2211.10763/) (2022)
- [Weakly-supervised Temporal Path Representation Learning with Contrastive Curriculum Learning -- Extended Version](https://mlsanity.com/paper/2203.16110/) (2022)
- [Curriculum Graph Machine Learning: A Survey](https://mlsanity.com/paper/2302.02926/) (2023)
- [Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2410.21042/) (2024)
- [Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classification](https://mlsanity.com/paper/2505.01660/) (2025)
- [Paraphrase Identification with Deep Learning: A Review of Datasets and Methods](https://mlsanity.com/paper/2212.06933/) (2022)
- [Learning to Predict Trustworthiness with Steep Slope Loss](https://mlsanity.com/paper/2110.00054/) (2021)
- [A Survey of Deep Long-Tail Classification Advancements](https://mlsanity.com/paper/2404.15593/) (2024)
- [Hierarchical Knowledge Guided Learning for Real-world Retinal Diseases Recognition](https://mlsanity.com/paper/2111.08913/) (2021)
- [Geometric Prior Guided Feature Representation Learning for Long-Tailed Classification](https://mlsanity.com/paper/2401.11436/) (2024)
- [A Comprehensive Survey on Imbalanced Data Learning](https://mlsanity.com/paper/2502.08960/) (2025)
- [Improving Facial Attribute Recognition by Group and Graph Learning](https://mlsanity.com/paper/2105.13825/) (2021)

## 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.