Multimodal deep learning systems that employ multiple modalities like text, image, audio,
video, etc., are showing better performance than individual modalities (ie, unimodal) …

Deep neural networks for computer vision are deployed in increasingly safety-critical and
socially-impactful applications, motivating the need to close the gap in model performance …

Test-time adaptation provides an effective means of tackling the potential distribution shift
between model training and inference, by dynamically updating the model at test time. This …

A model must adapt itself to generalize to new and different data during testing. In this
setting of fully test-time adaptation the model has only the test data and its own parameters …

Abstract Convolutional Neural Networks (CNNs) have advanced existing medical systems
for automatic disease diagnosis. However, there are still concerns about the reliability of …

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 …

Abstract Recent advances on Vision Transformer (ViT) and its improved variants have
shown that self-attention-based networks surpass traditional Convolutional Neural Networks …

Data augmentation is a simple yet effective way to improve the robustness of deep neural
networks (DNNs). Diversity and hardness are two complementary dimensions of data …

Since out-of-distribution generalization is a generally ill-posed problem, various proxy
targets (eg, calibration, adversarial robustness, algorithmic corruptions, invariance across …