Abstract Visual Attention Networks (VAN) with Large Kernel Attention (LKA) modules have
been shown to provide remarkable performance, that surpasses Vision Transformers (ViTs) …

The" Roaring 20s" of visual recognition began with the introduction of Vision Transformers
(ViTs), which quickly superseded ConvNets as the state-of-the-art image classification …

Since experiencing domain shifts during test-time is inevitable in practice, test-time adaption
(TTA) continues to adapt the model after deployment. Recently, the area of continual and …

Test-time adaptation harnesses test inputs to improve the accuracy of a model trained on
source data when tested on shifted target data. Most methods update the source model by …

We introduce a set of image transformations that can be used as corruptions to evaluate the
robustness of models as well as data augmentation mechanisms for training neural …

In real-world applications of machine learning, reliable and safe systems must consider
measures of performance beyond standard test set accuracy. These other goals include out …

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

In recent years, there have been attempts to increase the kernel size of Convolutional
Neural Nets (CNNs) to mimic the global receptive field of Vision Transformers'(ViTs) self …

Deep neural networks on 3D point cloud data have been widely used in the real world,
especially in safety-critical applications. However, their robustness against corruptions is …

The literature on robustness towards common corruptions shows no consensus on whether
adversarial training can improve the performance in this setting. First, we show that, when …