A top-down manner-based DCNN architecture for semantic image segmentation

Abstract

Given their powerful feature representation for recognition, deep convolutional neural networks (DCNNs) have been driving rapid advances in high-level computer vision tasks. However, their performance in semantic image segmentation is still not satisfactory. Based on the analysis of visual mechanism, we conclude that DCNNs in a bottom-up manner are not… (More)
DOI: 10.1371/journal.pone.0174508

Topics

8 Figures and Tables

Cite this paper

@inproceedings{Qiao2017ATM, title={A top-down manner-based DCNN architecture for semantic image segmentation}, author={Kai Qiao and Jian Chen and Linyuan Wang and Lei Zeng and Bin Yan}, booktitle={PloS one}, year={2017} }