Research map / Label-efficient and robust learning / Recognition and long-tail
Supercharging Imbalanced Data Learning With Energy-based Contrastive Representation Transfer
Junya Chen, Zidi Xiu, Benjamin Goldstein, Ricardo Henao, Lawrence Carin, Chenyang Tao
Read the paperCheck your idea against 137,217 papers
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 multiple class-dependent source priors instead of one shared prior (ablation) | ECRT · CIFAR100 | Top-1 accuracy: 52.31 -> 53.00 | Improved |
| Use multiple class-dependent source priors instead of one shared prior (ablation) | ECRT · iNaturalist | Top-1 accuracy: 68.38 -> 69.01 | Improved |
| Use multiple class-dependent source priors instead of one shared prior (ablation) | ECRT · TinyImageNet | Top-1 accuracy: 62.46 -> 64.40 | Improved |
| Use multiple class-dependent source priors instead of one shared prior (ablation) | ECRT · ArXiv | accuracy: 48.33 -> 48.33 | No clear effect |
| Train the feature encoder on majority and minority classes rather than only majority classes (ablation) | ECRT · CIFAR100 | Top-1 accuracy: 53.00 -> 51.79 | Hurt |
| Add causal augmentation (ablation) | ECRT · Toy model | accuracy | Improved |
| Increase augmentation strength when minority sample size is small (ablation) | ECRT · Toy model | accuracy | Hurt |
| Model directly in source space rather than feature space (ablation) | ECRT · Toy model | learning speed | Improved |
| Use parametric augmentation rather than nonparametric coordinate shuffling (ablation) | ECRT · Low-sample augmentation | MMD distance to ground truth | Improved |
Closest papers by meaning
- ConR: Contrastive Regularizer for Deep Imbalanced Regression (ICLR 2024 · similarity 0.88)
- Rethinking the Value of Labels for Improving Class-Imbalanced Learning (NeurIPS 2020 · similarity 0.87)
- Leveraging Group Classification with Descending Soft Labeling for Deep Imbalanced Regression (AAAI 2025 · similarity 0.87)
- BaCon: Boosting Imbalanced Semi-supervised Learning via Balanced Feature-Level Contrastive Learning (AAAI 2024 · similarity 0.86)
- A Tale of Two Classes: Adapting Supervised Contrastive Learning to Binary Imbalanced Datasets (CVPR 2025 · similarity 0.86)
- Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Data (ICML 2025 · similarity 0.85)
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.
