Multilevel Adaptive-Scale Context Aggregating Network for Semantic Segmentation in High-Resolution Remote Sensing Images
Xiao Li, Lin Lei, Gangyao Kuang
Abstract
High-resolution remote sensing (HR <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> S) images contain complex land objects of difference sizes, and it is important for semantic segmentation of the HR <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> S images to extract multiscale information. In this letter, we introduce a novel multilevel adaptive-scale context aggregating network (MACANet) for semantic segmentation of the HR <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> S images, which mainly consists of two parts—adaptive-scale context extraction block (AS-CEB) and sequential aggregation block (SAB). In particular, the AS-CEB introduces an inflexible strategy to obtain the features with appropriate scale information based on different asymmetric convolutions and the gated mechanism. Meanwhile, the SAB progressively aggregates multilevel adaptive-scale features, which are used to relieve the semantic gap between different-level features and generate precise score maps. Experimental results on representative HR <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> S datasets show the advantages of our method. The code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/RSIP-NUDT/MACANet</uri> .