When transferring a pretrained model to a downstream task, two popular methods are full
fine-tuning (updating all the model parameters) and linear probing (updating only the last …

AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …

Recent works in self-supervised learning have advanced the state-of-the-art by relying on
the contrastive learning paradigm, which learns representations by pushing positive pairs, or …

We consider unsupervised domain adaptation (UDA), where labeled data from a source
domain (eg, photos) and unlabeled data from a target domain (eg, sketches) are used to …

We investigate a practical domain adaptation task, called source-free domain adaptation
(SFUDA), where the source pretrained model is adapted to the target domain without access …

Machine learning models often perform poorly on subgroups that are underrepresented in
the training data. Yet, little is understood on the variation in mechanisms that cause …

Self-training and contrastive learning have emerged as leading techniques for incorporating
unlabeled data, both under distribution shift (unsupervised domain adaptation) and when it …

Real-world classification problems must contend with domain shift, the (potential) mismatch
between the domain where a model is deployed and the domain (s) where the training data …

Contrastive learning is a highly effective method for learning representations from unlabeled
data. Recent works show that contrastive representations can transfer across domains …

The increasing reliance on ML models in high-stakes tasks has raised a major concern
about fairness violations. Although there has been a surge of work that improves algorithmic …