Chaoning Zhang

research

∙ 09/21/2023

DimCL: Dimensional Contrastive Learning For Improving Self-Supervised Learning

Self-supervised learning (SSL) has gained remarkable success, for which ...

0 Thanh Nguyen, et al. ∙

research

∙ 09/11/2023

CNN or ViT? Revisiting Vision Transformers Through the Lens of Convolution

The success of Vision Transformer (ViT) has been widely reported on a wi...

0 Chenghao Li, et al. ∙

research

∙ 07/25/2023

FedMEKT: Distillation-based Embedding Knowledge Transfer for Multimodal Federated Learning

Federated learning (FL) enables a decentralized machine learning paradig...

0 Huy Q. Le, et al. ∙

research

∙ 07/07/2023

Swin Transformer-Based Dynamic Semantic Communication for Multi-User with Different Computing Capacity

Semantic communication has gained significant attention from researchers...

0 Loc X. Nguyen, et al. ∙

research

∙ 06/25/2023

Faster Segment Anything: Towards Lightweight SAM for Mobile Applications

Segment anything model (SAM) is a prompt-guided vision foundation model ...

0 Chaoning Zhang, et al. ∙

research

∙ 06/23/2023

Robustness of Segment Anything Model (SAM) for Autonomous Driving in Adverse Weather Conditions

Segment Anything Model (SAM) has gained considerable interest in recent ...

0 Xinru Shan, et al. ∙

research

∙ 06/13/2023

Robustness of SAM: Segment Anything Under Corruptions and Beyond

Segment anything model (SAM), as the name suggests, is claimed to be cap...

0 Yu Qiao, et al. ∙

research

∙ 06/03/2023

Segment Anything Meets Semantic Communication

In light of the diminishing returns of traditional methods for enhancing...

0 Shehbaz Tariq, et al. ∙

research

∙ 05/10/2023

When ChatGPT for Computer Vision Will Come? From 2D to 3D

ChatGPT and its improved variant GPT4 have revolutionized the NLP field ...

0 Chenghao Li, et al. ∙

research

∙ 05/10/2023

Generative AI meets 3D: A Survey on Text-to-3D in AIGC Era

Generative AI (AIGC, a.k.a. AI generated content) has made remarkable pr...

0 Chenghao Li, et al. ∙

research

∙ 05/01/2023

Attack-SAM: Towards Evaluating Adversarial Robustness of Segment Anything Model

Segment Anything Model (SAM) has attracted significant attention recentl...

0 Chenshuang Zhang, et al. ∙

research

∙ 04/29/2023

Segment Anything Model (SAM) Meets Glass: Mirror and Transparent Objects Cannot Be Easily Detected

Meta AI Research has recently released SAM (Segment Anything Model) whic...

0 Dongsheng Han, et al. ∙

research

∙ 04/15/2023

What if we have Meta GPT? From Content Singularity to Human-Metaverse Interaction in AIGC Era

The global metaverse development is facing a "cooldown moment", while th...

0 Lik-Hang Lee, et al. ∙

research

∙ 04/04/2023

A Survey on Graph Diffusion Models: Generative AI in Science for Molecule, Protein and Material

Diffusion models have become a new SOTA generative modeling method in va...

0 Mengchun Zhang, et al. ∙

research

∙ 04/04/2023

One Small Step for Generative AI, One Giant Leap for AGI: A Complete Survey on ChatGPT in AIGC Era

OpenAI has recently released GPT-4 (a.k.a. ChatGPT plus), which is demon...

0 Chaoning Zhang, et al. ∙

research

∙ 04/01/2023

MP-FedCL: Multi-Prototype Federated Contrastive Learning for Edge Intelligence

Federated learning-assisted edge intelligence enables privacy protection...

0 Yu Qiao, et al. ∙

research

∙ 03/23/2023

A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AI

Generative AI has demonstrated impressive performance in various fields,...

0 Chenshuang Zhang, et al. ∙

research

∙ 03/21/2023

A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?

As ChatGPT goes viral, generative AI (AIGC, a.k.a AI-generated content) ...

0 Chaoning Zhang, et al. ∙

research

∙ 03/14/2023

Text-to-image Diffusion Model in Generative AI: A Survey

This survey reviews text-to-image diffusion models in the context that d...

0 Chenshuang Zhang, et al. ∙

research

∙ 08/11/2022

On the Pros and Cons of Momentum Encoder in Self-Supervised Visual Representation Learning

Exponential Moving Average (EMA or momentum) is widely used in modern se...

0 Trung Pham, et al. ∙

research

∙ 07/30/2022

A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond

Masked autoencoders are scalable vision learners, as the title of MAE <c...

0 Chaoning Zhang, et al. ∙

research

∙ 07/22/2022

Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial Robustness

Adversarial training (AT) for robust representation learning and self-su...

0 Chaoning Zhang, et al. ∙

research

∙ 03/30/2022

Investigating Top-k White-Box and Transferable Black-box Attack

Existing works have identified the limitation of top-1 attack success ra...

0 Chaoning Zhang, et al. ∙

research

∙ 03/30/2022

Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCo

Contrastive learning (CL) is widely known to require many negative sampl...

0 Chaoning Zhang, et al. ∙

research

∙ 03/30/2022

How Does SimSiam Avoid Collapse Without Negative Samples? A Unified Understanding with Self-supervised Contrastive Learning

To avoid collapse in self-supervised learning (SSL), a contrastive loss ...

0 Chaoning Zhang, et al. ∙

research

∙ 03/09/2022

Practical No-box Adversarial Attacks with Training-free Hybrid Image Transformation

In recent years, the adversarial vulnerability of deep neural networks (...

1 Qilong Zhang, et al. ∙

research

∙ 02/11/2022

Noise Augmentation Is All You Need For FGSM Fast Adversarial Training: Catastrophic Overfitting And Robust Overfitting Require Different Augmentation

Adversarial training (AT) and its variants are the most effective approa...

0 Chaoning Zhang, et al. ∙

research

∙ 10/06/2021

Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNs

Convolutional Neural Networks (CNNs) have become the de facto gold stand...

22 Philipp Benz, et al. ∙

research

∙ 04/19/2021

Restoration of Video Frames from a Single Blurred Image with Motion Understanding

We propose a novel framework to generate clean video frames from a singl...

0 Dawit Mureja Argaw, et al. ∙

research

∙ 04/07/2021

Universal Adversarial Training with Class-Wise Perturbations

Despite their overwhelming success on a wide range of applications, conv...

0 Philipp Benz, et al. ∙

research

∙ 03/02/2021

A Brief Survey on Deep Learning Based Data Hiding, Steganography and Watermarking

Data hiding is the art of concealing messages with limited perceptual ch...

0 Chaoning Zhang, et al. ∙

research

∙ 03/02/2021

A Survey On Universal Adversarial Attack

Deep neural networks (DNNs) have demonstrated remarkable performance for...

0 Chaoning Zhang, et al. ∙

research

∙ 02/12/2021

Universal Adversarial Perturbations Through the Lens of Deep Steganography: Towards A Fourier Perspective

The booming interest in adversarial attacks stems from a misalignment be...

0 Chaoning Zhang, et al. ∙

research

∙ 12/30/2020

Towards Robust Data Hiding Against (JPEG) Compression: A Pseudo-Differentiable Deep Learning Approach

Data hiding is one widely used approach for protecting authentication an...

0 Chaoning Zhang, et al. ∙

research

∙ 10/26/2020

Robustness May Be at Odds with Fairness: An Empirical Study on Class-wise Accuracy

Recently, convolutional neural networks (CNNs) have made significant adv...

0 Philipp Benz, et al. ∙

research

∙ 10/23/2020

ResNet or DenseNet? Introducing Dense Shortcuts to ResNet

ResNet or DenseNet? Nowadays, most deep learning based approaches are im...

0 Chaoning Zhang, et al. ∙

research

∙ 10/07/2020

Revisiting Batch Normalization for Improving Corruption Robustness

Modern deep neural networks (DNN) have demonstrated remarkable success i...

0 Philipp Benz, et al. ∙

research

∙ 10/07/2020

Batch Normalization Increases Adversarial Vulnerability: Disentangling Usefulness and Robustness of Model Features

Batch normalization (BN) has been widely used in modern deep neural netw...

0 Philipp Benz, et al. ∙

research

∙ 10/07/2020

CD-UAP: Class Discriminative Universal Adversarial Perturbation

A single universal adversarial perturbation (UAP) can be added to all na...

8 Chaoning Zhang, et al. ∙

research

∙ 10/07/2020

Double Targeted Universal Adversarial Perturbations

Despite their impressive performance, deep neural networks (DNNs) are wi...

1 Philipp Benz, et al. ∙

research

∙ 07/13/2020

Data from Model: Extracting Data from Non-robust and Robust Models

The essence of deep learning is to exploit data to train a deep neural n...

0 Philipp Benz, et al. ∙

research

∙ 07/13/2020

Understanding Adversarial Examples from the Mutual Influence of Images and Perturbations

A wide variety of works have explored the reason for the existence of ad...

17 Chaoning Zhang, et al. ∙

Chaoning Zhang

Featured Co-authors