Research map / Label-efficient and robust learning / Recognition and long-tail
Delving into Semantic Scale Imbalance
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Apply semantic-scale reweighting to RIDE | RIDE · ImageNet-LT | Top-1 accuracy (Overall): 56.1 -> 58.2 | Helped |
| Apply semantic-scale reweighting to RIDE | RIDE · iNaturalist2018 | Top-1 accuracy (Overall): 72.6 -> 73.4 | Helped |
| Apply semantic-scale reweighting to CE | CE with ResNet-18 · ImageNet | Top-1 accuracy: 70.1 -> 71.2 | Helped |
| Apply semantic-scale reweighting to CE | CE with ResNet-18 · CIFAR-100 | Top-1 accuracy: 75.6 -> 76.9 | Helped |
| Apply semantic-scale reweighting to SoftTriple | SoftTriple · CUB-2011 | Recall@1: 65.4 -> 66.4 | Helped |
| Apply semantic-scale reweighting to SoftTriple | SoftTriple · Cars196 | Recall@1: 84.5 -> 85.6 | Helped |
| Apply semantic-scale reweighting to SoftTriple | SoftTriple · CIFAR-100-LT, imbalance factor 200 | Recall@1: 46.6 -> 49.3 | Helped |
| Apply semantic-scale reweighting to cRT | cRT · MSCOCO-GLT, CLT protocol | Accuracy: 73.64 -> 76.82 | Helped |
| Increase the warm-up duration n beyond the selected value (ablation) | Dynamic semantic-scale-balanced learning · Training | Model performance | No clear effect |
Closest papers by meaning
- Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance (ICML 2024 · similarity 0.89)
- Rethinking the Bias of Foundation Model under Long-tailed Distribution (ICML 2025 · similarity 0.88)
- Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Data (ICML 2025 · similarity 0.88)
- Learning under Localized Minority Imbalance (NeurIPS 2026 · similarity 0.87)
- Class-Attribute Priors: Adapting Optimization to Heterogeneity and Fairness Objective (AAAI 2024 · similarity 0.85)
- Twice Class Bias Correction for Imbalanced Semi-supervised Learning (AAAI 2024 · 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.