A Divide-and-Conquer Approach towards Understanding Deep Networks

by   Weilin Fu, et al.

Deep neural networks have achieved tremendous success in various fields including medical image segmentation. However, they have long been criticized for being a black-box, in that interpretation, understanding and correcting architectures is difficult as there is no general theory for deep neural network design. Previously, precision learning was proposed to fuse deep architectures and traditional approaches. Deep networks constructed in this way benefit from the original known operator, have fewer parameters, and improved interpretability. However, they do not yield state-of-the-art performance in all applications. In this paper, we propose to analyze deep networks using known operators, by adopting a divide-and-conquer strategy to replace network components, whilst retaining its performance. The task of retinal vessel segmentation is investigated for this purpose. We start with a high-performance U-Net and show by step-by-step conversion that we are able to divide the network into modules of known operators. The results indicate that a combination of a trainable guided filter and a trainable version of the Frangi filter yields a performance at the level of U-Net (AUC 0.974 vs. 0.972) with a tremendous reduction in parameters (111,536 vs. 9,575). In addition, the trained layers can be mapped back into their original algorithmic interpretation and analyzed using standard tools of signal processing.



There are no comments yet.


page 3

page 7


Searching Learning Strategy with Reinforcement Learning for 3D Medical Image Segmentation

Deep neural network (DNN) based approaches have been widely investigated...

Assessing the Role of Random Forests in Medical Image Segmentation

Neural networks represent a field of research that can quickly achieve v...

WaveSNet: Wavelet Integrated Deep Networks for Image Segmentation

In deep networks, the lost data details significantly degrade the perfor...

Attention Guided Network for Retinal Image Segmentation

Learning structural information is critical for producing an ideal resul...

Deep Algorithms: designs for networks

A new design methodology for neural networks that is guided by tradition...

Leveraging Image Complexity in Macro-Level Neural Network Design for Medical Image Segmentation

Recent progress in encoder-decoder neural network architecture design ha...

Accurate and Lightweight Image Super-Resolution with Model-Guided Deep Unfolding Network

Deep neural networks (DNNs) based methods have achieved great success in...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.