Deep neural networks (DNNs) are machine learning algorithms that have revolutionized
computer vision due to their remarkable successes in tasks like object classification and …

This paper revisits the standard pretrain-then-finetune paradigm used in computer vision for
visual recognition tasks. Typically, state-of-the-art foundation models are pretrained using …

Computer vision models have known performance disparities across attributes such as
gender and skin tone. This means during tasks such as classification and detection, model …

Abstract Contrastive Language-Image Pre-training (CLIP) models have demonstrated
remarkable generalization capabilities across multiple challenging distribution shifts …

Abstract Machine learning models have been found to learn shortcuts---unintended decision
rules that are unable to generalize---undermining models' reliability. Previous works address …

People are relying on AI agents to assist them with various tasks. The human must know
when to rely on the agent, collaborate with the agent, or ignore its suggestions. In this work …

Despite excellent average-case performance of many image classifiers, their performance
can substantially deteriorate on semantically coherent subgroups of the data that were …

Data augmentation (DA) encodes invariance and provides implicit regularization critical to a
model's performance in image classification tasks. However, while DA improves average …

Synthetic image datasets offer unmatched advantages for designing and evaluating deep
neural networks: they make it possible to (i) render as many data samples as needed,(ii) …

The proliferation of pretrained models, as a result of advancements in pretraining
techniques, has led to the emergence of a vast zoo of publicly available models. Effectively …