Self-supervised learning (SSL) has gained remarkable success, for which
...
The success of Vision Transformer (ViT) has been widely reported on a wi...
Federated learning (FL) enables a decentralized machine learning paradig...
Semantic communication has gained significant attention from researchers...
Segment anything model (SAM) is a prompt-guided vision foundation model ...
Segment Anything Model (SAM) has gained considerable interest in recent ...
Segment anything model (SAM), as the name suggests, is claimed to be cap...
In light of the diminishing returns of traditional methods for enhancing...
ChatGPT and its improved variant GPT4 have revolutionized the NLP field ...
Generative AI (AIGC, a.k.a. AI generated content) has made remarkable
pr...
Segment Anything Model (SAM) has attracted significant attention recentl...
Meta AI Research has recently released SAM (Segment Anything Model) whic...
The global metaverse development is facing a "cooldown moment", while th...
Diffusion models have become a new SOTA generative modeling method in va...
OpenAI has recently released GPT-4 (a.k.a. ChatGPT plus), which is
demon...
Federated learning-assisted edge intelligence enables privacy protection...
Generative AI has demonstrated impressive performance in various fields,...
As ChatGPT goes viral, generative AI (AIGC, a.k.a AI-generated content) ...
This survey reviews text-to-image diffusion models in the context that
d...
Exponential Moving Average (EMA or momentum) is widely used in modern
se...
Masked autoencoders are scalable vision learners, as the title of MAE
<c...
Adversarial training (AT) for robust representation learning and
self-su...
Existing works have identified the limitation of top-1 attack success ra...
Contrastive learning (CL) is widely known to require many negative sampl...
To avoid collapse in self-supervised learning (SSL), a contrastive loss ...
In recent years, the adversarial vulnerability of deep neural networks (...
Adversarial training (AT) and its variants are the most effective approa...
Convolutional Neural Networks (CNNs) have become the de facto gold stand...
We propose a novel framework to generate clean video frames from a singl...
Despite their overwhelming success on a wide range of applications,
conv...
Data hiding is the art of concealing messages with limited perceptual
ch...
Deep neural networks (DNNs) have demonstrated remarkable performance for...
The booming interest in adversarial attacks stems from a misalignment be...
Data hiding is one widely used approach for protecting authentication an...
Recently, convolutional neural networks (CNNs) have made significant
adv...
ResNet or DenseNet? Nowadays, most deep learning based approaches are
im...
Modern deep neural networks (DNN) have demonstrated remarkable success i...
Batch normalization (BN) has been widely used in modern deep neural netw...
A single universal adversarial perturbation (UAP) can be added to all na...
Despite their impressive performance, deep neural networks (DNNs) are wi...
The essence of deep learning is to exploit data to train a deep neural
n...
A wide variety of works have explored the reason for the existence of
ad...