Skip to content
Free planNo credit card requiredStart writing
AI for Research home
AI for Research home
Dashboard
Sign inGet started

article · Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering · 2020

LEARNING DENSE CONTEXTUAL FEATURES FOR SEMANTIC SEGMENTATION

Hacer Yalım Keleş, Long Ang Lim

Cited by 0Open access

Abstract

Semantic segmentation, which is one of the key problems in computer vision, has been applied in various application domains such as autonomous driving, robot navigation, or medical imagery, to name a few. Recently, deep learning, especially deep neural networks, have shown significant performance improvement over conventional semantic segmentation methods. In this paper, we present a novel encoder-decoder type deep neural network-based method, namely XSeNet, that can be trained end-to-end in a supervised manner. We adapt ResNet-50 layers as the encoder and design a cascaded decoder that composes of the stack of the X-Modules, which enables the network to learning dense contextual information and having wider field-of-view. We evaluate our method using CamVid dataset, and experimental results reveal that our method can segment most part of the scene accurately and even outperforms previous state-of-the art methods.

Cite this paper

APA 7

Keleş, H. Y., & Lim, L. A. (2020). LEARNING DENSE CONTEXTUAL FEATURES FOR SEMANTIC SEGMENTATION. Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering, 62(1), 26–34. https://doi.org/10.33769/aupse.611958

MLA 9

Keleş, Hacer Yalım, and Long Ang Lim. “LEARNING DENSE CONTEXTUAL FEATURES FOR SEMANTIC SEGMENTATION.” Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering, vol. 62, no. 1, 2020, pp. 26–34, https://doi.org/10.33769/aupse.611958.

Chicago

Keleş, Hacer Yalım, and Long Ang Lim. 2020. “LEARNING DENSE CONTEXTUAL FEATURES FOR SEMANTIC SEGMENTATION.” Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering 62 (1): 26–34. https://doi.org/10.33769/aupse.611958.

Harvard

Keleş, H.Y. and Lim, L.A. (2020) ‘LEARNING DENSE CONTEXTUAL FEATURES FOR SEMANTIC SEGMENTATION’, Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering, 62(1), pp. 26–34. Available at: https://doi.org/10.33769/aupse.611958.

BibTeX
@article{keles2020learning,
  title = {{LEARNING DENSE CONTEXTUAL FEATURES FOR SEMANTIC SEGMENTATION}},
  author = {Keleş, Hacer Yalım and Lim, Long Ang},
  journal = {Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering},
  volume = {62},
  number = {1},
  pages = {26--34},
  year = {2020},
  doi = {10.33769/aupse.611958}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.

Related papers

A

Rihard Karba, Juš Kocijan, Tadej Bajd et al. · International series on intelligent systems, control and automation: science and engineering · 2023

Cited by 0