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 d...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/9/2671 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | 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 <i>VariGAN</i>, 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 <i>VariGAN</i> backbone exhibits superior performance across diverse content and style domains. <i>VariGAN</i> improved class IoU by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>236</mn><mo>%</mo></mrow></semantics></math></inline-formula> and participant identification by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>195</mn><mo>%</mo></mrow></semantics></math></inline-formula> compared to <i>CycleGAN</i>. |
|---|---|
| ISSN: | 1424-8220 |