Search Results for author:
Found 2 papers, 0 papers with code
How does Contrastive Pre-training Connect Disparate Domains?
We develop a conceptual model for contrastive learning under domain shifts, where data augmentations form connections between classes and domains that can be far apart.
Fine-Tuning Distorts Pretrained Features and Underperforms Out-of-Distribution
It is well known that fine-tuning leads to better accuracy in-distribution (ID).
Cannot find the paper you are looking for? You can
Submit a new open access paper.
