Mapping Auto-context Decision Forests to Deep ConvNets for Semantic Segmentation

TL;DR

This paper demonstrates how Auto-context Decision Forests can be mapped to deep ConvNets for improved semantic segmentation, enabling end-to-end training and better performance with limited data.

Contribution

It introduces a novel architecture mapping Auto-context to deep ConvNets, allowing end-to-end training and improved segmentation performance in limited data scenarios.

Findings

Auto-context can be mapped to a deep ConvNet architecture.

The mapping enables end-to-end training of ConvNets from Decision Forests.

The approach outperforms stacked Decision Forests in computer vision and biology applications.

Abstract

We consider the task of pixel-wise semantic segmentation given a small set of labeled training images. Among two of the most popular techniques to address this task are Decision Forests (DF) and Neural Networks (NN). In this work, we explore the relationship between two special forms of these techniques: stacked DFs (namely Auto-context) and deep Convolutional Neural Networks (ConvNet). Our main contribution is to show that Auto-context can be mapped to a deep ConvNet with novel architecture, and thereby trained end-to-end. This mapping can be used as an initialization of a deep ConvNet, enabling training even in the face of very limited amounts of training data. We also demonstrate an approximate mapping back from the refined ConvNet to a second stacked DF, with improved performance over the original. We experimentally verify that these mappings outperform stacked DFs for two different applications in computer vision and biology: Kinect-based body part labeling from depth images, and somite segmentation in microscopy images of developing zebrafish. Finally, we revisit the core mapping from a Decision Tree (DT) to a NN, and show that it is also possible to map a fuzzy DT, with sigmoidal split decisions, to a NN. This addresses multiple limitations of the previous mapping, and yields new insights into the popular Rectified Linear Unit (ReLU), and more recently proposed concatenated ReLU (CReLU), activation functions.