all AI news
DLUNet: Semi-supervised Learning based Dual-Light UNet for Multi-organ Segmentation. (arXiv:2209.10984v1 [eess.IV])
cs.CV updates on arXiv.org arxiv.org
The manual ground truth of abdominal multi-organ is labor-intensive. In order
to make full use of CT data, we developed a semi-supervised learning based
dual-light UNet. In the training phase, it consists of two light UNets, which
make full use of label and unlabeled data simultaneously by using
consistent-based learning. Moreover, separable convolution and residual
concatenation was introduced light UNet to reduce the computational cost.
Further, a robust segmentation loss was applied to improve the performance. In
the inference phase, …
arxiv light segmentation semi-supervised semi-supervised learning supervised learning unet