Dynamic High-Resolution Network for Semantic Segmentation in Remote-Sensing Images
-
Published:2023-04-26
Issue:9
Volume:15
Page:2293
-
ISSN:2072-4292
-
Container-title:Remote Sensing
-
language:en
-
Short-container-title:Remote Sensing
Author:
Guo Shichen12, Yang Qi23, Xiang Shiming23ORCID, Wang Pengfei1, Wang Xuezhi1
Affiliation:
1. Computer Network Information Center, Chinese Academy of Sciences, Beijing 100083, China 2. University of Chinese Academy of Sciences, Beijing 100049, China 3. State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
Abstract
Semantic segmentation of remote-sensing (RS) images is one of the most fundamental tasks in the understanding of a remote-sensing scene. However, high-resolution RS images contain plentiful detailed information about ground objects, which scatter everywhere spatially and have variable sizes, styles, and visual appearances. Due to the high similarity between classes and diversity within classes, it is challenging to obtain satisfactory and accurate semantic segmentation results. This paper proposes a Dynamic High-Resolution Network (DyHRNet) to solve this problem. Our proposed network takes HRNet as a super-architecture, aiming to leverage the important connections and channels by further investigating the parallel streams at different resolution representations of the original HRNet. The learning task is conducted under the framework of a neural architecture search (NAS) and channel-wise attention module. Specifically, the Accelerated Proximal Gradient (APG) algorithm is introduced to iteratively solve the sparse regularization subproblem from the perspective of neural architecture search. In this way, valuable connections are selected for cross-resolution feature fusion. In addition, a channel-wise attention module is designed to weight the channel contributions for feature aggregation. Finally, DyHRNet fully realizes the dynamic advantages of data adaptability by combining the APG algorithm and channel-wise attention module simultaneously. Compared with nine classical or state-of-the-art models (FCN, UNet, PSPNet, DeepLabV3+, OCRNet, SETR, SegFormer, HRNet+FCN, and HRNet+OCR), DyHRNet has shown high performance on three public challenging RS image datasets (Vaihingen, Potsdam, and LoveDA). Furthermore, the visual segmentation results, the learned structures, the iteration process analysis, and the ablation study all demonstrate the effectiveness of our proposed model.
Funder
Key Research Program of Frontier Sciences, CAS National Key Research and Development Program of China National Natural Science Foundation of China
Subject
General Earth and Planetary Sciences
Reference66 articles.
1. Semantic Labeling in very High Resolution Images via A Self-cascaded Convolutional Neural Network;Liu;ISPRS J. Photogramm. Remote Sens.,2018 2. Li, L., Yao, J., Liu, Y., Yuan, W., Shi, S., and Yuan, S. (2017). Optimal Seamline Detection for Orthoimage Mosaicking by Combining Deep Convolutional Neural Network and Graph Cuts. Remote Sens., 9. 3. Panboonyuen, T., Jitkajornwanich, K., Lawawirojwong, S., Srestasathiern, P., and Vateekul, P. (2019). Semantic Segmentation on Remotely Sensed Images Using an Enhanced Global Convolutional Network with Channel Attention and Domain Specific Transfer Learning. Remote Sens., 11. 4. Guo, S., Jin, Q., Wang, H., Wang, X., Wang, Y., and Xiang, S. (2019). Learnable Gated Convolutional Neural Network for Semantic Segmentation in Remote-Sensing Images. Remote Sens., 11. 5. Multiscale U-Shaped CNN Building Instance Extraction Framework with Edge Constraint for High-Spatial-Resolution Remote Sensing Imagery;Liu;IEEE Trans. Geosci. Remote Sens.,2021
|
|