CLIP, as a foundational vision language model, is widely used in zero-sh...
Certifiably robust defenses against adversarial patches for image classi...
Common deep neural networks (DNNs) for image classification have been sh...
Deep neural networks often exhibit poor performance on data that is unli...
Convolutional neural networks (CNNs) learn to extract representations of...
Deep neural networks (DNNs) have been shown to over-fit a dataset when b...
Deep neural networks achieve state-of-the-art results on several tasks w...
Classifiers such as deep neural networks have been shown to be vulnerabl...