In this paper, we investigate the adversarial robustness of vision
trans...
We present Diversity-Aware Meta Visual Prompting (DAM-VP), an efficient ...
Recent studies have shown that CLIP has achieved remarkable success in
p...
Notwithstanding the prominent performance achieved in various applicatio...
This paper presents a simple yet effective framework MaskCLIP, which
inc...
We propose bootstrapped masked autoencoders (BootMAE), a new approach fo...
Adversary and invisibility are two fundamental but conflict characters o...
In this work we propose Identity Consistency Transformer, a novel face
f...
This paper explores a better codebook for BERT pre-training of vision
tr...
We present Mobile-Former, a parallel design of MobileNet and Transformer...
We present CSWin Transformer, an efficient and effective Transformer-bas...
DeepFake detection has so far been dominated by “artifact-driven” method...
Deep neural networks have made tremendous progress in 3D point-cloud
rec...
Modern deep neural networks(DNNs) are vulnerable to adversarial samples....
As an efficient watermark attack method, geometric distortions destroy t...
Modern deep neural networks are often vulnerable to adversarial samples....
In this paper, we propose an improvement of Adversarial Transformation
N...