TY - GEN
T1 - Learning contextual information for indoor semantic segmentation
AU - Wang, Jianhua
AU - Zheng, Chuanxia
AU - Chen, Weihai
AU - Wu, Xingming
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/10/19
Y1 - 2016/10/19
N2 - Deep Convolutional Neural Networks(DCNNs) have recently shown great performance in many high-level vision tasks, such as image classification, object detection and more recently outdoor semantic segmentation. However, the convolutional layer only process the local regions in the image, ignoring the global context information. To overcome this poor localization property of Convolutional Neural Networks(CNNs), a new form of model that combine conditional random field(CRF) to CNNs is proposed. Hence, we train the CNNs to learn local pixel-wise information and then combine the CRF based on probabilistic graph model that are connected to global pixel. The experiment results on the public indoor NYUD v2 dataset demonstrate the proposed model outperform the existing state-of-the-art methods on a challenging 40 classes task, yielding a higher class average accuracy of 47.1% and pixel average accuracy of 66.4%.
AB - Deep Convolutional Neural Networks(DCNNs) have recently shown great performance in many high-level vision tasks, such as image classification, object detection and more recently outdoor semantic segmentation. However, the convolutional layer only process the local regions in the image, ignoring the global context information. To overcome this poor localization property of Convolutional Neural Networks(CNNs), a new form of model that combine conditional random field(CRF) to CNNs is proposed. Hence, we train the CNNs to learn local pixel-wise information and then combine the CRF based on probabilistic graph model that are connected to global pixel. The experiment results on the public indoor NYUD v2 dataset demonstrate the proposed model outperform the existing state-of-the-art methods on a challenging 40 classes task, yielding a higher class average accuracy of 47.1% and pixel average accuracy of 66.4%.
UR - https://www.scopus.com/pages/publications/84997483439
U2 - 10.1109/ICIEA.2016.7603848
DO - 10.1109/ICIEA.2016.7603848
M3 - 会议稿件
AN - SCOPUS:84997483439
T3 - Proceedings of the 2016 IEEE 11th Conference on Industrial Electronics and Applications, ICIEA 2016
SP - 1639
EP - 1644
BT - Proceedings of the 2016 IEEE 11th Conference on Industrial Electronics and Applications, ICIEA 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 11th IEEE Conference on Industrial Electronics and Applications, ICIEA 2016
Y2 - 5 June 2016 through 7 June 2016
ER -