Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Weiming Zhang

Weiming Zhang

Diversity-Aware Meta Visual Prompting

Mar 14, 2023
Qidong Huang, Xiaoyi Dong, Dongdong Chen, Weiming Zhang, Feifei Wang, Gang Hua, Nenghai Yu

Figure 1 for Diversity-Aware Meta Visual Prompting

Figure 2 for Diversity-Aware Meta Visual Prompting

Figure 3 for Diversity-Aware Meta Visual Prompting

Figure 4 for Diversity-Aware Meta Visual Prompting

* CVPR2023, code is available at https://github.com/shikiw/DAM-VP

Access Paper or Ask Questions

Pseudo Label-Guided Model Inversion Attack via Conditional Generative Adversarial Network

Feb 20, 2023
Xiaojian Yuan, Kejiang Chen, Jie Zhang, Weiming Zhang, Nenghai Yu, Yang Zhang

Figure 1 for Pseudo Label-Guided Model Inversion Attack via Conditional Generative Adversarial Network

Figure 2 for Pseudo Label-Guided Model Inversion Attack via Conditional Generative Adversarial Network

Figure 3 for Pseudo Label-Guided Model Inversion Attack via Conditional Generative Adversarial Network

Figure 4 for Pseudo Label-Guided Model Inversion Attack via Conditional Generative Adversarial Network

* Accepted by AAAI 2023

Access Paper or Ask Questions

DeAR: A Deep-learning-based Audio Re-recording Resilient Watermarking

Dec 13, 2022
Chang Liu, Jie Zhang, Han Fang, Zehua Ma, Weiming Zhang, Nenghai Yu

Figure 1 for DeAR: A Deep-learning-based Audio Re-recording Resilient Watermarking

Figure 2 for DeAR: A Deep-learning-based Audio Re-recording Resilient Watermarking

Figure 3 for DeAR: A Deep-learning-based Audio Re-recording Resilient Watermarking

Figure 4 for DeAR: A Deep-learning-based Audio Re-recording Resilient Watermarking

* Accepted by AAAI2023

Access Paper or Ask Questions

CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet

Dec 12, 2022
Xiaoyi Dong, Jianmin Bao, Ting Zhang, Dongdong Chen, Shuyang Gu, Weiming Zhang, Lu Yuan, Dong Chen, Fang Wen, Nenghai Yu

Figure 1 for CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet

Figure 2 for CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet

Figure 3 for CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet

Figure 4 for CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet

* Technical Report, code will be available at https://github.com/LightDXY/FT-CLIP

Access Paper or Ask Questions