Deep Structure Learning using Feature Extraction in Trained Projection Space

Abstract

Over the last decade of machine learning, convolutional neural networks have been the most striking successes for feature extraction of rich sensory and high-dimensional data. While learning data representations via convolutions is already well studied and efficiently implemented in various deep learning libraries, one often faces limited memory capacity and insufficient number of training data, especially for high-dimensional and large-scale tasks. To overcome these limitations, we introduce a network architecture using a self-adjusting and data dependent version of the Radon-transform (linear data projection), also known as x-ray projection, to enable feature extraction via convolutions in lower-dimensional space. The resulting framework, named PiNet, can be trained end-to-end and shows promising performance on volumetric segmentation tasks. We test proposed model on public datasets to show that our approach achieves comparable results only using fractional amount of parameters. Investigation of memory usage and processing time confirms PiNet's superior efficiency compared to other segmentation models.

References in corpus (7)

• ADADELTA: An Adaptive Learning Rate Method
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• A large annotated medical image dataset for the development and evaluation of segmentation algorithms
• Optimization for Medical Image Segmentation: Theory and Practice when evaluating with Dice Score or Jaccard Index
• Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation
• Monocular Depth Estimation Based On Deep Learning: An Overview
• Reinventing 2D Convolutions for 3D Images