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

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...

Full description

Bibliographic Details
Main Authors: Kunal Chaturvedi, Ali Braytee, Jun Li, Mukesh Prasad
Format: Article
Language:English
Published: MDPI AG 2023-03-01
Series:Sensors
Subjects:
generative adversarial networks
self-supervised learning
cut-and-paste
segmentation
Online Access:https://www.mdpi.com/1424-8220/23/7/3649

Internet

https://www.mdpi.com/1424-8220/23/7/3649

Similar Items