Spectral Normalized CycleGAN with Application in Semisupervised Semantic Segmentation of Sonar Images

The effectiveness of CycleGAN is demonstrated to outperform recent approaches for semisupervised semantic segmentation on public segmentation benchmarks. In contrast to analog images, however, the acoustic images are unbalanced and often exhibit speckle noise. As a consequence, CycleGAN is prone to...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Zhisheng, Tang, Jinsong, Zhong, Heping, Wu, Haoran, Zhang, Peng, Ning, Mingqiang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi 2022
Materias:
Research Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9071973/
https://www.ncbi.nlm.nih.gov/pubmed/35528354
http://dx.doi.org/10.1155/2022/1274260

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9071973/
https://www.ncbi.nlm.nih.gov/pubmed/35528354
http://dx.doi.org/10.1155/2022/1274260

Ejemplares similares