SS-CPGAN: Self-Supervised Cut-and-Pasting Generative Adversarial Network for Object Segmentation
This addresses the need for automated object segmentation and image composition in computer vision, reducing reliance on manual labeling, but appears incremental as it builds upon existing GAN and self-supervised techniques.
The paper tackles the problem of foreground object segmentation and realistic composite image generation without manual annotations by proposing a self-supervised Cut-and-Paste GAN, achieving significant performance improvements over state-of-the-art methods on standard benchmarks.
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.