Abstract Context Machine Learning (ML) has been at the heart of many innovations over the
past years. However, including it in so-called “safety-critical” systems such as automotive or …

We introduce four new real-world distribution shift datasets consisting of changes in image
style, image blurriness, geographic location, camera operation, and more. With our new …

Today's state-of-the-art machine vision models are vulnerable to image corruptions like
blurring or compression artefacts, limiting their performance in many real-world applications …

Recent work has indicated that, unlike humans, ImageNet-trained CNNs tend to classify
images by texture rather than by shape. How pervasive is this bias, and where does it come …

Current state-of-the-art object recognition models are largely based on convolutional neural
network (CNN) architectures, which are loosely inspired by the primate visual system …

Abstract Test-Time Adaptation (TTA) allows to update pre-trained models to changing data
distributions at deployment time. While early work tested these algorithms for individual fixed …

Although much progress has been made towards robust deep learning, a significant gap in
robustness remains between real-world perturbations and more narrowly defined sets …

Deep neural networks often exhibit poor performance on data that is unlikely under the train-
time data distribution, for instance data affected by corruptions. Previous works demonstrate …

Joint visual and language modeling on large-scale datasets has recently shown good
progress in multi-modal tasks when compared to single modal learning. However …

When designing a semantic segmentation model for a real-world application, such as
autonomous driving, it is crucial to understand the robustness of the network with respect to …