HZHaoyi Zhang
Haoyi Zhang
*This is an algorithmically generated author record based on publicly available information.
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Haoyi Zhang has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Dawei Guan
School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China
1 shared publication - Hang Zhou
School of Electronics and Information Engineering, Beijing Jiaotong University, Beijing 100082, China
1 shared publication - Xinping Lin
School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, China
1 shared publication
Latest Publications
- Open Access
VariGAN: Enhancing Image Style Transfer via UNet Generator, Depthwise Discriminator, and LPIPS Loss in Adversarial Learning Framework
Image style transfer is a challenging task that has gained significant attention in recent years due to its growing complexity. Training is typically performed using paradigms offered by GAN-based image style transfer networks. Cycle-based training methods provide an approach for handling unpaired data. Nevertheless, achieving high transfer quality remains a challenge with these methods due to the simplicity of the employed network. The purpose of this research is to present VariGAN, a novel approach that incorporates three additional strategies to optimize GAN-based image style transfer: (1) Improving the quality of transferred images by utilizing an effective UNet generator network in conjunction with a context-related feature extraction module. (2) Optimizing the training process while reducing dependency on the generator through the use of a depthwise discriminator. (3) Introducing LPIPS loss to further refine the loss function and enhance the overall generation quality of the framework. Through a series of experiments, we demonstrate that the VariGAN backbone exhibits superior performance across diverse content and style domains. VariGAN improved class IoU by and participant identification by compared to CycleGAN.Open AccessVariGAN: Enhancing Image Style Transfer via UNet Generator, Depthwise Discriminator, and LPIPS Loss in Adversarial Learning Framework
Image style transfer is a challenging task that has gained significant attention in recent years due to its growing complexity. Training is typically performed using paradigms offered by GAN-based image style transfer networks. Cycle-based training methods provide an approach for handling unpaired data. Nevertheless, achieving high transfer quality remains a challenge with these methods due to the simplicity of the employed network. The purpose of this research is to present VariGAN, a novel approach that incorporates three additional strategies to optimize GAN-based image style transfer: (1) Improving the quality of transferred images by utilizing an effective UNet generator network in conjunction with a context-related feature extraction module. (2) Optimizing the training process while reducing dependency on the generator through the use of a depthwise discriminator. (3) Introducing LPIPS loss to further refine the loss function and enhance the overall generation quality of the framework. Through a series of experiments, we demonstrate that the VariGAN backbone exhibits superior performance across diverse content and style domains. VariGAN improved class IoU by and participant identification by compared to CycleGAN.