Figure 1
From: Melanoma segmentation using deep learning with test-time augmentations and conditional random fields
The architectures of utilized UNet, ResUNet and ResUNet++ models. All three architectures have encoder, bridge, and decoder blocks. In all these blocks 3 \(\times\) 3 convolutional layers has been used except in output block, where a 1 \(\times\) 1 convolutional layer followed by a sigmoid function is used to convert segmentation map into the predicted mask. Combinedly, 21, 15 and 41 convolutional layers has been used in UNet, ResUNet and ResUNet++ architectures, respectively.
