Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks
2024-01-16
· ICLR 2024 spotlight ·
anchor
Findings
IC-1017
Vision and language models pre-trained on noisy data exhibit degraded OOD transfer that is partially recoverable via SVD-based feature-space regularization