Deep Learning is the most widely used tool in the contemporary field of computer vision. Its
ability to accurately solve complex problems is employed in vision research to learn deep …

Normalization techniques are essential for accelerating the training and improving the
generalization of deep neural networks (DNNs), and have successfully been used in various …

Monocular depth estimation is fundamental for 3D scene understanding and downstream
applications. However, even under the supervised setup, it is still challenging and ill-posed …

Self-supervised learning on graph-structured data has drawn recent interest for learning
generalizable, transferable and robust representations from unlabeled graphs. Among …

Transformers have been recently adapted for large scale image classification, achieving
high scores shaking up the long supremacy of convolutional neural networks. However the …

Prior work has studied different visual modalities in isolation and developed separate
architectures for recognition of images, videos, and 3D data. Instead, in this paper, we …

As a research community, we are still lacking a systematic understanding of the progress on
adversarial robustness which often makes it hard to identify the most promising ideas in …

Recently, Vision Transformers (ViTs) have been broadly explored in visual recognition. With
low efficiency in encoding fine-level features, the performance of ViTs is still inferior to the …

Vision Transformers have been the most popular network architecture in visual recognition
recently due to the strong ability of encode global information. However, its high …

We present VILLA, the first known effort on large-scale adversarial training for vision-and-
language (V+ L) representation learning. VILLA consists of two training stages:(i) task …