Learning Deconvolution Network for Semantic Segmentation

Abstract

We propose a novel semantic segmentation algorithm by learning a deep deconvolution network. We learn the network on top of the convolutional layers adopted from VGG 16-layer net. The deconvolution network is composed of deconvolution and unpooling layers, which identify pixelwise class labels and predict segmentation masks. We apply the trained network to each proposal in an input image, and construct the final semantic segmentation map by combining the results from all proposals in a simple manner. The proposed algorithm mitigates the limitations of the existing methods based on fully convolutional networks by integrating deep deconvolution network and proposal-wise prediction, our segmentation method typically identifies detailed structures and handles objects in multiple scales naturally. Our network demonstrates outstanding performance in PASCAL VOC 2012 dataset, and we achieve the best accuracy (72.5%) among the methods trained without using Microsoft COCO dataset through ensemble with the fully convolutional network.

DOI: 10.1109/ICCV.2015.178
View Slides

Extracted Key Phrases

0200400201520162017
Citations per Year

600 Citations

Semantic Scholar estimates that this publication has 600 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{Noh2015LearningDN, title={Learning Deconvolution Network for Semantic Segmentation}, author={Hyeonwoo Noh and Seunghoon Hong and Bohyung Han}, journal={2015 IEEE International Conference on Computer Vision (ICCV)}, year={2015}, pages={1520-1528} }