As a special type of transformer, vision transformers (ViTs) can be used for various computer
vision (CV) applications. Convolutional neural networks (CNNs) have several potential …

Backdoor defenses have been studied to alleviate the threat of deep neural networks
(DNNs) being backdoor attacked and thus maliciously altered. Since DNNs usually adopt …

Abstract Vision Transformer (ViT), as a powerful alternative to Convolutional Neural Network
(CNN), has received much attention. Recent work showed that ViTs are also vulnerable to …

Abstract Contrastive Vision-Language Pre-training known as CLIP has shown promising
effectiveness in addressing downstream image recognition tasks. However recent works …

Abstract Although Vision transformers (ViTs) have recently dominated many vision tasks,
deploying ViT models on resource-limited devices remains a challenging problem. To …

Abstract Domain generalization (DG) aims to learn a model that generalizes well to unseen
target domains utilizing multiple source domains without re-training. Most existing DG works …

Recent studies revealed that using third-party models may lead to backdoor threats, where
adversaries can maliciously manipulate model predictions based on backdoors implanted …

Recently, MLP-like vision models have achieved promising performances on mainstream
visual recognition tasks. In contrast with vision transformers and CNNs, the success of MLP …

In this paper, we investigate the adversarial robustness of vision transformers that are
equipped with BERT pretraining (eg, BEiT, MAE). A surprising observation is that MAE has …

As agricultural applications are specialized, plant diseases are diverse, and there is a lack of
agricultural datasets, current plant disease identification performance is inadequate. In this …