A few years ago, the first CNN surpassed human performance on ImageNet. However, it
soon became clear that machines lack robustness on more challenging test cases, a major …

Autonomous vehicles (AV) require that neural networks used for perception be robust to
different viewpoints if they are to be deployed across many types of vehicles without the …

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) …

For more than a decade, researchers have measured progress in object recognition on
ImageNet-based generalization benchmarks such as ImageNet-A,-C, and-R. Recent …

Computer vision research has long aimed to build systems that are robust to transformations
found in natural data. Traditionally, this is done using data augmentation or hard-coding …

For more than a decade, researchers have measured progress in object recognition on the
ImageNet dataset along with its associated generalization benchmarks such as ImageNet-A …

Visual object recognition systems need to generalize from a set of 2D training views to novel
views. The question of how the human visual system can generalize to novel views has …

Symmetries (transformations by group actions) are present in many datasets, and leveraging
them holds significant promise for improving predictions in machine learning. In this work …

Existing works show that although modern neural networks achieve remarkable
generalization performance on the in-distribution (ID) dataset, the accuracy drops …

Deep learning is closing the gap with human vision on several object recognition
benchmarks. Here we investigate this gap for challenging images where objects are seen in …