SS-CPGAN: Self-Supervised Cut-and-Pasting Generative Adversarial Network for Object Segmentation

This paper proposes a novel self-supervised based Cut-and-Paste GAN to perform foreground object segmentation and generate realistic composite images without manual annotations. We accomplish this goal by a simple yet effective self-supervised approach coupled with the U-Net discriminator. The propo...

Descripción completa

Detalles Bibliográficos
Autores principales: Chaturvedi, Kunal, Braytee, Ali, Li, Jun, Prasad, Mukesh
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Communication
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10098536/
https://www.ncbi.nlm.nih.gov/pubmed/37050712
http://dx.doi.org/10.3390/s23073649

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10098536/
https://www.ncbi.nlm.nih.gov/pubmed/37050712
http://dx.doi.org/10.3390/s23073649

Ejemplares similares