Deep Deconvolutional Networks for Scene Parsing

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.

Cited by in corpus (12)

• Embedding Structured Contour and Location Prior in Siamesed Fully Convolutional Networks for Road Detection
• Progressive LiDAR Adaptation for Road Detection
• TBC-Net: A real-time detector for infrared small target detection using semantic constraint
• Multi-Residual Networks: Improving the Speed and Accuracy of Residual Networks
• Joint Attention in Driver-Pedestrian Interaction: from Theory to Practice
• Fast LIDAR-based Road Detection Using Fully Convolutional Neural Networks
• Discriminatively Boosted Image Clustering with Fully Convolutional Auto-Encoders
• Pixel-wise Segmentation of Street with Neural Networks
• Data-Driven Modeling of Geometry-Adaptive Steady Heat Transfer based on Convolutional Neural Networks: Heat Conduction
• Convolutional Recurrent Network for Road Boundary Extraction
• DAGMapper: Learning to Map by Discovering Lane Topology
• Hierarchical Recurrent Attention Networks for Structured Online Maps