1.3k citations · 1.7k across the 20 of their papers we have counts for
3 papers · 2 filters
On the Initialization of Long Short-Term Memory Networks
Mostafa Mehdipour Ghazi, Mads Nielsen, Akshay Pai +4
Weight initialization is important for faster convergence and stability of deep neural networks training. In this paper, a robust initialization method is developed to address the…
One Network to Segment Them All: A General, Lightweight System for Accurate 3D Medical Image Segmentation
Mathias Perslev, Erik Bjørnager Dam, Akshay Pai +1
Many recent medical segmentation systems rely on powerful deep learning models to solve highly specific tasks. To maximize performance, it is standard practice to evaluate numerous…
Knowledge distillation for semi-supervised domain adaptation
Mauricio Orbes-Arteaga, Jorge Cardoso, Lauge Sørensen +5
In the absence of sufficient data variation (e.g., scanner and protocol variability) in annotated data, deep neural networks (DNNs) tend to overfit during training. As a result, th…