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

no code implementations • 1 Jan 2023 • Kunal Chaturvedi, Ali Braytee, Jun Li, Mukesh Prasad

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.

Generative Adversarial Network Semantic Segmentation