Research map / Label-efficient and robust learning / Recognition and long-tail
A Re-Balancing Strategy for Class-Imbalanced Classification Based on Instance Difficulty
Sihao Yu, Jiafeng Guo, Ruqing Zhang, Yixing Fan, Zizhen Wang, Xueqi Cheng
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use instance-level sampling weights based on learning-speed difficulty | ResNet-32 · Long-tailed CIFAR-10, imbalance ratio 100 | accuracy (%): 72.2 -> 75.0 | Improved |
| Use instance-level sampling weights based on learning-speed difficulty | ResNet-32 · Long-tailed CIFAR-100, imbalance ratio 100 | accuracy (%): 40.6 -> 42.3 | Improved |
| Combine TDE with instance-level re-sampling | ResNet-32 · Long-tailed CIFAR-100, imbalance ratio 100 | accuracy (%): 43.5 -> 44.9 | Improved |
| Increase the minority-class weights further | Class-Balance Loss · Long-tailed CIFAR-100, imbalance ratio 100 | overall accuracy (%): 41.1 -> 38.2 | Hurt |
| Use instance-level difficulty re-sampling | Multilayer Perceptron · Long-tailed MNIST binary classification | overall accuracy (%): 86.04 -> 87.99 | Improved |
| Apply instance-level re-sampling | Logistic Regression · UCI classification datasets (average) | accuracy (%): 74.9 -> 78.2 | Improved |
| Apply instance-level re-sampling | ResNet-50 · iNaturalist 2019 | accuracy (%): 70.19% -> 71.08% | Improved |
| Apply instance-level re-sampling | ResNet-101 · iNaturalist 2019 | accuracy (%): 72.84% -> 73.32% | Improved |
Closest papers by meaning
- Gradient Reweighting: Towards Imbalanced Class-Incremental Learning (CVPR 2024 · similarity 0.88)
- Learning under Localized Minority Imbalance (NeurIPS 2026 · similarity 0.88)
- Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance (ICML 2024 · similarity 0.87)
- Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Data (ICML 2025 · similarity 0.87)
- Synthetic Tabular Data Generation for Imbalanced Classification: The Surprising Effectiveness of an Overlap Class (AAAI 2025 · similarity 0.87)
- Class-Attribute Priors: Adapting Optimization to Heterogeneity and Fairness Objective (AAAI 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
