manuscript.pdf (914.91 kB)
Download fileSSL-Unet: A Self-Supervised Learning Strategy Base on U-Net for Retinal Vessel Segmentation
We propose a SSL-Unet model for retinal vascular segmentation as well as two self-supervised training strategies. The strategy can help the self-supervised module to learn pseudo labels for improving the segmentation performance. Moreover, the fusion of both self-supervised and supervised paradigms is applied to retinal segmentation for the first time. Meanwhile, it can also be extended to any segmentation network.
History
Email Address of Submitting Author
macsy@cqnu.edu.cnSubmitting Author's Institution
CQNUSubmitting Author's Country
- China