error correctionIn the multi-target segmentation network proposed in this paper the main component of the encoder is the CNN backbone network In order to select a more suitable backbone network we eva

In the multi-target segmentation network proposed in this paper, the main component of the encoder is the CNN backbone network. To select a more suitable backbone network, we evaluated the major backbone networks on dataset #1 and dataset #2. In these experiments, all parameters were consistent except for the backbone network. We used RESNET-50 and CoTNet-50 as backbone networks and trained and tested them on the constructed dataset. The test results are shown in Table 5 and Table 6.