Name: Ning Yu
Type: User
Company: Netflix Eyeline Studios
Bio: Research Scientist at Netflix Eyeline Studios. Ex-Salesforce. Joint Ph.D. from UMD & MPI-INF. Leading efforts in visual and multimodal generative AI.
Twitter: realNingYu
Location: Los Angeles, CA
Blog: https://ningyu1991.github.io/
Ning Yu's Projects
The official PyTorch implementation for ICCV'21 Oral paper 'Artificial GAN Fingerprints: Rooting Deepfake Attribution in Training Data'
The official TensorFlow implementation for ICCV'21 paper 'Dual Contrastive Loss and Attention for GANs'
Caffe: a fast open framework for deep learning.
Code for the paper: CNN-generated images are surprisingly easy to spot... for now https://peterwang512.github.io/CNNDetection/
Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV 2020, in PyTorch)
The official Caffe implementation for WACV'18 paper 'Learning to Detect Multiple Photographic Defects'
The official Tensorflow implementation for ICCV'19 paper 'Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints'
The source code of CVPR19 'Im2Pencil: Controllable Pencil Illustration from Photographs'.
The official Tensorflow implementation for ECCV'20 paper 'Inclusive GAN: Improving Data and Minority Coverage in Generative Models'
Ning Yu's personal homepage.
The official TensorFlow implementation for ICLR'22 Spotlight paper 'Responsible Disclosure of Generative Models Using Scalable Fingerprinting'
The official Tensorflow implementation for CVPR'19 paper 'Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture'
The source code of NIPS17 'Universal Style Transfer via Feature Transforms'.