Picture for Ngai-Man Cheung

Ngai-Man Cheung

Exploring Incompatible Knowledge Transfer in Few-shot Image Generation

Apr 15, 2023
Yunqing Zhao, Chao Du, Milad Abdollahzadeh, Tianyu Pang, Min Lin, Shuicheng Yan, Ngai-Man Cheung

Figure 1 for Exploring Incompatible Knowledge Transfer in Few-shot Image Generation

Figure 2 for Exploring Incompatible Knowledge Transfer in Few-shot Image Generation

Figure 3 for Exploring Incompatible Knowledge Transfer in Few-shot Image Generation

Figure 4 for Exploring Incompatible Knowledge Transfer in Few-shot Image Generation

* 25 pages, 16 figures, 10 tables. The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023

Access Paper or Ask Questions

Re-thinking Model Inversion Attacks Against Deep Neural Networks

Apr 04, 2023
Ngoc-Bao Nguyen, Keshigeyan Chandrasegaran, Milad Abdollahzadeh, Ngai-Man Cheung

Figure 1 for Re-thinking Model Inversion Attacks Against Deep Neural Networks

Figure 2 for Re-thinking Model Inversion Attacks Against Deep Neural Networks

Figure 3 for Re-thinking Model Inversion Attacks Against Deep Neural Networks

Figure 4 for Re-thinking Model Inversion Attacks Against Deep Neural Networks

* Accepted to CVPR 2023. The first two authors contributed equally

Access Paper or Ask Questions

A Recipe for Watermarking Diffusion Models

Mar 17, 2023
Yunqing Zhao, Tianyu Pang, Chao Du, Xiao Yang, Ngai-Man Cheung, Min Lin

Figure 1 for A Recipe for Watermarking Diffusion Models

Figure 2 for A Recipe for Watermarking Diffusion Models

Figure 3 for A Recipe for Watermarking Diffusion Models

Figure 4 for A Recipe for Watermarking Diffusion Models

* 23 pages, 22 figures

Access Paper or Ask Questions

Fair Generative Models via Transfer Learning

Dec 02, 2022
Christopher TH Teo, Milad Abdollahzadeh, Ngai-Man Cheung

Figure 1 for Fair Generative Models via Transfer Learning

Figure 2 for Fair Generative Models via Transfer Learning

Figure 3 for Fair Generative Models via Transfer Learning

Figure 4 for Fair Generative Models via Transfer Learning

* Accepted in AAAI-2023

Access Paper or Ask Questions

Few-shot Image Generation via Adaptation-Aware Kernel Modulation

Nov 13, 2022
Yunqing Zhao, Keshigeyan Chandrasegaran, Milad Abdollahzadeh, Ngai-Man Cheung

Figure 1 for Few-shot Image Generation via Adaptation-Aware Kernel Modulation

Figure 2 for Few-shot Image Generation via Adaptation-Aware Kernel Modulation

Figure 3 for Few-shot Image Generation via Adaptation-Aware Kernel Modulation

Figure 4 for Few-shot Image Generation via Adaptation-Aware Kernel Modulation

* The Thirty-Sixth Annual Conference on Neural Information Processing Systems (NeurIPS 2022), 14 pages

Access Paper or Ask Questions

Discovering Transferable Forensic Features for CNN-generated Images Detection

Aug 24, 2022
Keshigeyan Chandrasegaran, Ngoc-Trung Tran, Alexander Binder, Ngai-Man Cheung

Figure 1 for Discovering Transferable Forensic Features for CNN-generated Images Detection

Figure 2 for Discovering Transferable Forensic Features for CNN-generated Images Detection

Figure 3 for Discovering Transferable Forensic Features for CNN-generated Images Detection

Figure 4 for Discovering Transferable Forensic Features for CNN-generated Images Detection

* ECCV 2022 Oral; 35 pages

Access Paper or Ask Questions

FS-BAN: Born-Again Networks for Domain Generalization Few-Shot Classification

Aug 24, 2022
Yunqing Zhao, Ngai-Man Cheung

Figure 1 for FS-BAN: Born-Again Networks for Domain Generalization Few-Shot Classification

Figure 2 for FS-BAN: Born-Again Networks for Domain Generalization Few-Shot Classification

Figure 3 for FS-BAN: Born-Again Networks for Domain Generalization Few-Shot Classification

Figure 4 for FS-BAN: Born-Again Networks for Domain Generalization Few-Shot Classification

Access Paper or Ask Questions