class imbalance
A situation in classification tasks where certain classes have significantly more instances than others, often leading to biased model performance. Handling class imbalance is crucial to ensure fair and accurate predictions across all classes.
- CORAL: Disentangling Latent Representations in Long-Tailed Diffusion
- Class-wise Balancing Data Replay for Federated Class-Incremental Learning
- Class-wise Balancing Data Replay for Federated Class-Incremental Learning
- Fourier Clouds: Fast Bias Correction for Imbalanced Semi-Supervised Learning
- Geometric Imbalance in Semi-Supervised Node Classification
- Improved Balanced Classification with Theoretically Grounded Loss Functions
- Learning Dense Hand Contact Estimation from Imbalanced Data
- QuanDA: Quantile-Based Discriminant Analysis for High-Dimensional Imbalanced Classification
- STARC-9: A Large-scale Dataset for Multi-Class Tissue Classification for CRC Histopathology
- Sample-Efficient Multi-Round Generative Data Augmentation for Long-Tail Instance Segmentation
- Self-Perturbed Anomaly-Aware Graph Dynamics for Multivariate Time-Series Anomaly Detection
- Stratify or Die: Rethinking Data Splits in Image Segmentation
- TS-MOF: Two-Stage Multi-Objective Fine-tuning for Long-Tailed Recognition
- Tree-Sliced Entropy Partial Transport
- Vertical Federated Feature Screening