CODA: A Correlation-Oriented Disentanglement and Augmentation Modeling Scheme for Better Resisting Subpopulation Shifts
–Neural Information Processing Systems
Data-driven models learned often struggle to generalize due to widespread subpopulation shifts, especially the presence of both spurious correlations and group imbalance (SC-GI).
Neural Information Processing Systems
Oct-10-2025, 14:39:40 GMT
- Country:
- Asia
- China
- Guangdong Province > Shenzhen (0.04)
- Hong Kong (0.04)
- Macao (0.04)
- China
- North America > United States
- Virginia (0.04)
- Asia
- Genre:
- Research Report
- Experimental Study (1.00)
- New Finding (0.67)
- Research Report
- Industry:
- Banking & Finance (0.46)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning > Neural Networks (1.00)
- Representation & Reasoning (0.92)
- Vision (1.00)
- Information Technology > Artificial Intelligence