Gated Convolutional Neural Network for Semantic Segmentation in High-Resolution ImagesReportar como inadecuado


Gated Convolutional Neural Network for Semantic Segmentation in High-Resolution Images


Gated Convolutional Neural Network for Semantic Segmentation in High-Resolution Images - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

1

National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, 95 Zhongguancun East Road, Beijing 100190, China

2

University of Chinese Academy of Sciences, Beijing 101408, China

3

Alibaba Group, Beijing 100102, China





*

Author to whom correspondence should be addressed.



Academic Editors: Qi Wang, Nicolas H. Younan, Carlos López-Martínez, Xiaofeng Li and Prasad S. Thenkabail

Abstract Semantic segmentation is a fundamental task in remote sensing image processing. The large appearance variations of ground objects make this task quite challenging. Recently, deep convolutional neural networks DCNNs have shown outstanding performance in this task. A common strategy of these methods e.g., SegNet for performance improvement is to combine the feature maps learned at different DCNN layers. However, such a combination is usually implemented via feature map summation or concatenation, indicating that the features are considered indiscriminately. In fact, features at different positions contribute differently to the final performance. It is advantageous to automatically select adaptive features when merging different-layer feature maps. To achieve this goal, we propose a gated convolutional neural network to fulfill this task. Specifically, we explore the relationship between the information entropy of the feature maps and the label-error map, and then a gate mechanism is embedded to integrate the feature maps more effectively. The gate is implemented by the entropy maps, which are generated to assign adaptive weights to different feature maps as their relative importance. Generally, the entropy maps, i.e., the gates, guide the network to focus on the highly-uncertain pixels, where detailed information from lower layers is required to improve the separability of these pixels. The selected features are finally combined to feed into the classifier layer, which predicts the semantic label of each pixel. The proposed method achieves competitive segmentation accuracy on the public ISPRS 2D Semantic Labeling benchmark, which is challenging for segmentation by only using the RGB images. View Full-Text

Keywords: semantic segmentation; CNN; deep learning; ISPRS; remote sensing; gate semantic segmentation; CNN; deep learning; ISPRS; remote sensing; gate





Autor: Hongzhen Wang 1,2, Ying Wang 1, Qian Zhang 3, Shiming Xiang 1,* and Chunhong Pan 1

Fuente: http://mdpi.com/



DESCARGAR PDF




Documentos relacionados