U-Net won the award for the most challenging Grand Challenge for the Computer-Automated Detection of Caries in Bitewing Radiography at the International Symposium on Biomedical Imaging (ISBI) 2015 and also won the Cell Tracking Challenge at ISBI in 2015.
U-Net is the fastest and most precise semantic segmentation architecture. It outperformed methods such as the sliding window CNN at the ISBI challenge for semantic segmentation of neuron structures in electron microscopic stacks.
At ISBI 2015, it also won the two most challenging transmitted light microscopy categories, Phase contrast and DIC microscopy, by a large margin.
The main idea behind U-Net is to add successive layers to a normal contracting network, where upsampling operators replace pooling operations. Due to this, the layers of U-Net increase the resolution of the output. The most important modification in U-Net occurs in the upsampling...
