Deep Deconvolutional Networks for Scene Parsing

TL;DR

This paper introduces a novel deep deconvolutional neural network architecture for scene parsing that learns higher order image structures and spatial priors, achieving state-of-the-art results without post-processing.

Contribution

It proposes a new network combining deconvolutional networks with CNNs and introduces multi-patch training for scene parsing.

Findings

Achieves state-of-the-art performance on four datasets.

Capable of learning higher order image structures.

Operates without post-processing steps.

Abstract

Scene parsing is an important and challenging prob- lem in computer vision. It requires labeling each pixel in an image with the category it belongs to. Tradition- ally, it has been approached with hand-engineered features from color information in images. Recently convolutional neural networks (CNNs), which automatically learn hierar- chies of features, have achieved record performance on the task. These approaches typically include a post-processing technique, such as superpixels, to produce the final label- ing. In this paper, we propose a novel network architecture that combines deep deconvolutional neural networks with CNNs. Our experiments show that deconvolutional neu- ral networks are capable of learning higher order image structure beyond edge primitives in comparison to CNNs. The new network architecture is employed for multi-patch training, introduced as part of this work. Multi-patch train- ing makes it possible to effectively learn spatial priors from scenes. The proposed approach yields state-of-the-art per- formance on four scene parsing datasets, namely Stanford Background, SIFT Flow, CamVid, and KITTI. In addition, our system has the added advantage of having a training system that can be completely automated end-to-end with- out requiring any post-processing.