96 citations · 187 across the 4 of their papers we have counts for
Showing cs.CVShow all
2 papers · 1 filter
cs.CV2020★ 23 cited
Comparing Normalization Methods for Limited Batch Size Segmentation Neural Networks
Martin Kolarik, Radim Burget, Kamil Riha
The widespread use of Batch Normalization has enabled training deeper neural networks with more stable and faster results. However, the Batch Normalization works best using large b…
cs.CV2020
Planar 3D Transfer Learning for End to End Unimodal MRI Unbalanced Data Segmentation
Martin Kolarik, Radim Burget, Carlos M. Travieso-Gonzalez +1
We present a novel approach of 2D to 3D transfer learning based on mapping pre-trained 2D convolutional neural network weights into planar 3D kernels. The method is validated by th…