English

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

Computer Vision and Pattern Recognition 2023-04-06 v3 Machine Learning

Abstract

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 based discriminator. The proposed method extends the ability of the standard discriminators to learn not only the global data representations via classification (real/fake) but also learn semantic and structural information through pseudo labels created using the self-supervised task. The proposed method empowers the generator to create meaningful masks by forcing it to learn informative per-pixel as well as global image feedback from the discriminator. Our experiments demonstrate that our proposed method significantly outperforms the state-of-the-art methods on the standard benchmark datasets.

Keywords

Cite

@article{arxiv.2301.00366,
  title  = {SS-CPGAN: Self-Supervised Cut-and-Pasting Generative Adversarial Network for Object Segmentation},
  author = {Kunal Chaturvedi and Ali Braytee and Jun Li and Mukesh Prasad},
  journal= {arXiv preprint arXiv:2301.00366},
  year   = {2023}
}
R2 v1 2026-06-28T07:58:39.690Z