AIConfPaper
← Search

Xiangping Zeng

2 accepted papers

2021

Mask-Embedded Discriminator With Region-Based Semantic Regularization for Semi-Supervised Class-Conditional Image Synthesis

Yi Liu, Xiaoyang Huo, Tianyi Chen, Xiangping Zeng, Si Wu, Zhiwen Yu +1
CVPR 2021poster

Semi-supervised generative learning (SSGL) makes use of unlabeled data to achieve a trade-off between the data collection/annotation effort and generation performance, when adequate labeled data are not available. Learning precise class semantics is crucial for class-conditional image synthesis with…

Cited by 6PDF ↗Scholar ↗
2020

Regularizing Discriminative Capability of CGANs for Semi-Supervised Generative Learning

Yi Liu, Guangchang Deng, Xiangping Zeng, Si Wu, Zhiwen Yu, Hau-San Wong
CVPR 2020poster

Semi-supervised generative learning aims to learn the underlying class-conditional distribution of partially labeled data. Generative Adversarial Networks (GANs) have led to promising progress in this task. However, it still needs to further explore the issue of imbalance between real labeled data a…

Cited by 29PDF ↗Scholar ↗