Timezone: »

Masked Generative Adversarial Networks are Data-Efficient Generation Learners
Jiaxing Huang · Kaiwen Cui · Dayan Guan · Aoran Xiao · Fangneng Zhan · Shijian Lu · Shengcai Liao · Eric Xing

Tue Nov 29 09:00 AM -- 11:00 AM (PST) @ Hall J #913

This paper shows that masked generative adversarial network (MaskedGAN) is robust image generation learners with limited training data. The idea of MaskedGAN is simple: it randomly masks out certain image information for effective GAN training with limited data. We develop two masking strategies that work along orthogonal dimensions of training images, including a shifted spatial masking that masks the images in spatial dimensions with random shifts, and a balanced spectral masking that masks certain image spectral bands with self-adaptive probabilities. The two masking strategies complement each other which together encourage more challenging holistic learning from limited training data, ultimately suppressing trivial solutions and failures in GAN training. Albeit simple, extensive experiments show that MaskedGAN achieves superior performance consistently across different network architectures (e.g., CNNs including BigGAN and StyleGAN-v2 and Transformers including TransGAN and GANformer) and datasets (e.g., CIFAR-10, CIFAR-100, ImageNet, 100-shot, AFHQ, FFHQ and Cityscapes).

Author Information

Jiaxing Huang (Nanyang Technological University)
Kaiwen Cui (Nanyang Technological University)
Dayan Guan (Mohamed bin Zayed University of Artificial Intelligence)
Aoran Xiao (Nanyang Technological University)
Fangneng Zhan (Max Planck Institute for Informatics)
Shijian Lu (Nanyang Technological University)
Shengcai Liao (Inception Institute of Artificial Intelligence (IIAI))

Shengcai Liao is a Lead Scientist in the Inception Institute of Artificial Intelligence (IIAI), Abu Dhabi, UAE. He is a Senior Member of IEEE. Previously, he was an Associate Professor in the Institute of Automation, Chinese Academy of Sciences (CASIA). He received the B.S. degree in mathematics from the Sun Yat-sen University in 2005 and the Ph.D. degree from CASIA in 2010. He was a Postdoc in the Michigan State University during 2010-2012. His research interests include object detection, recognition, and tracking, especially face and person related tasks. He has published over 100 papers, with **over 14,900 citations and h-index 43** according to Google Scholar. He **ranks 905 among 215,114 scientists (Top 0.42%)** in 2019 single year in the field of AI, according to a study by Stanford University of Top 2% world-wide scientists. His representative work LOMO+XQDA, known for effective feature design and metric learning for person re-identification, has been **cited over 1,900 times and ranks top 10 among 602 papers in CVPR 2015**. He was awarded the Best Student Paper in ICB 2006, ICB 2015, and CCBR 2016, and the Best Paper in ICB 2007. He was also awarded the IJCB 2014 Best Reviewer and CVPR 2019/2021 Outstanding Reviewer. He was an Assistant Editor for the book “Encyclopedia of Biometrics (2nd Ed.)”. He will serve as Program Chair for IJCB 2022, and Area Chair for CVPR 2022 and ECCV 2022. He served as Area Chairs for ICPR 2016, ICB 2016 and 2018, SPC for IJCAI 2021, and reviewers for ICCV, CVPR, ECCV, NeurIPS, ICLR, AAAI, TPAMI, IJCV, TNNLS, etc. He was the Winner of the CVPR 2017 Detection in Crowded Scenes Challenge and ICCV 2019 NightOwls Pedestrian Detection Challenge.

Eric Xing (Petuum Inc.)

More from the Same Authors