Class-Wise Fully Convolutional Network for Semantic Segmentation of Remote Sensing Images

Abstract

Semantic segmentation is a fundamental task in remote sensing image interpretation, which aims to assign a semantic label for every pixel in the given image. Accurate semantic segmentation is still challenging due to the complex distributions of various ground objects. With the development of deep learning, a series of segmentation networks represented by fully convolutional network (FCN) has made remarkable progress on this problem, but the segmentation accuracy is still far from expectations. This paper focuses on the importance of class-specific features of different land cover objects, and presents a novel end-to-end class-wise processing framework for segmentation. The proposed class-wise FCN (C-FCN) is shaped in the form of an encoder-decoder structure with skip-connections, in which the encoder is shared to produce general features for all categories and the decoder is class-wise to process class-specific features. To be detailed, class-wise transition (CT), class-wise up-sampling (CU), class-wise supervision (CS), and class-wise classification (CC) modules are designed to achieve the class-wise transfer, recover the resolution of class-wise feature maps, bridge the encoder and modified decoder, and implement class-wise classifications, respectively. Class-wise and group convolutions are adopted in the architecture with regard to the control of parameter numbers. The method is tested on the public ISPRS 2D semantic labeling benchmark datasets. Experimental results show that the proposed C-FCN significantly improves the segmentation performances compared with many state-of-the-art FCN-based networks, revealing its potentials on accurate segmentation of complex remote sensing images.

A Combined Convolutional Neural Network for Urban Land-Use Classification with GIS Data

“…Compared with the existing results of the aforementioned Dual Attention Feature fusion [54] and Class-Wise FCN [55], our method improved the results in classes of building and others, but was lower in car class. With the target of generating the land use classification of an urban area into the bigger and continuous block, our method will do better for bigger classes on images.…”

“…In particular, the high accuracy of identifying the building class in the Potsdam datasets is due to the fact that people live in similar residential areas with similar architectural features, proving that the method in this paper takes into account the correlation between neighboring pixels of buildings. The recent proposed Dual Attention Feature fusion method [54] and Class-Wise FCN [55] also use these two datasets, and we compared the performances with the DAU-Net. Table 6 shows the results.…”

Multi‐scale network for remote sensing segmentation

“…Some works [22][23][24][25][26][27] have proposed special methods based on the characteristics of remote sensing images. Kampffmeyer et al [28] proposed a remote sensing image segmentation method based on FCN.…”

“…Some works [22‐27] have proposed special methods based on the characteristics of remote sensing images. Kampffmeyer et al.…”

Short-Term Power Prediction of a Photovoltaic Power Station Based on the SSA-CEEMDAN-FCN Model

“…Some people also combined WT with a deep convolutional neural network (DCNN) and proposed a WT DCNN hybrid method for photovoltaic power generation prediction [ 28 ]. FCN is more flexible than CNN in processing time series data [ 29 , 30 ]. Time series data can be input with any sequence length, and more sequence data features can be retained after FCN.…”