Transformers are models that implement a mechanism of self-attention, individually
weighting the importance of each part of the input data. Their use in image classification …

Object detection is a crucial task in computer vision (CV). With the rapid advancement of
Transformer-based models in natural language processing (NLP) and various visual tasks …

Adversarial purification refers to a class of defense methods that remove adversarial
perturbations using a generative model. These methods do not make assumptions on the …

Recent studies show that Vision Transformers (ViTs) exhibit strong robustness against
various corruptions. Although this property is partly attributed to the self-attention …

Abstract Visual Counterfactual Explanations (VCEs) are an important tool to understand the
decisions of an image classifier. They are “small” but “realistic” semantic changes of the …

Following the success in advancing natural language processing and understanding,
transformers are expected to bring revolutionary changes to computer vision. This work …

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

Abstract 3D object detection is an essential perception task in autonomous driving to
understand the environments. The Bird's-Eye-View (BEV) representations have significantly …

The robustness of deep neural networks is frequently compromised when faced with
adversarial examples, common corruptions, and distribution shifts, posing a significant …

We propose an end-to-end Multitask Learning Transformer framework, named MulT, to
simultaneously learn multiple high-level vision tasks, including depth estimation, semantic …