Fully Connected Deep Structured Networks

TL;DR

This paper introduces a unified deep learning model that combines feature extraction and global graphical modeling into a single trainable network for semantic segmentation, demonstrating promising results on PASCAL VOC 2012.

Contribution

It proposes a novel fully connected deep structured network that integrates local and global information in a single training process for semantic segmentation.

Findings

Achieved competitive results on PASCAL VOC 2012

Unified training improves segmentation accuracy

Simplifies the traditional two-stage approach

Abstract

Convolutional neural networks with many layers have recently been shown to achieve excellent results on many high-level tasks such as image classification, object detection and more recently also semantic segmentation. Particularly for semantic segmentation, a two-stage procedure is often employed. Hereby, convolutional networks are trained to provide good local pixel-wise features for the second step being traditionally a more global graphical model. In this work we unify this two-stage process into a single joint training algorithm. We demonstrate our method on the semantic image segmentation task and show encouraging results on the challenging PASCAL VOC 2012 dataset.