CySGAN: Cyclic Segmentation Generative Adversarial Network

doi:doi:10.57702/r21dylur

CySGAN: Cyclic Segmentation Generative Adversarial Network

Instance segmentation for unlabeled imaging modalities is a challenging but essential task as collecting expert annotation can be expensive and time-consuming. Existing works segment a new modality by either deploying a pre-trained model optimized on diverse training data or conducting domain translation and image segmentation as two independent steps.

BibTex:

@dataset{Leander_Lauenburg_and_Zudi_Lin_and_Ruihan_Zhang_and_M´arcia_dos_Santos_and_Siyu_Huang_and_Ignacio_Arganda-Carreras_and_Edward_S_Boyden_and_Hanspeter_Pﬁster_and_Donglai_Wei_2024,
    abstract = {Instance segmentation for unlabeled imaging modalities is a challenging but essential task as collecting expert annotation can be expensive and time-consuming. Existing works segment a new modality by either deploying a pre-trained model optimized on diverse training data or conducting domain translation and image segmentation as two independent steps.},
    author = {Leander Lauenburg and Zudi Lin and Ruihan Zhang and M´arcia dos Santos and Siyu Huang and Ignacio Arganda-Carreras and Edward S. Boyden and Hanspeter Pﬁster and Donglai Wei},
    doi = {10.57702/r21dylur},
    institution = {No Organization},
    keyword = {'Cyclic Segmentation', 'Generative Adversarial Network', 'Instance Segmentation', 'Unlabeled Modalities'},
    month = {dec},
    publisher = {TIB},
    title = {CySGAN: Cyclic Segmentation Generative Adversarial Network},
    url = {https://service.tib.eu/ldmservice/dataset/cysgan--cyclic-segmentation-generative-adversarial-network},
    year = {2024}
}