CS-HSNet: A Cross-Siamese Change Detection Network Based on Hierarchical-Split Attention
Open Access
- 21 September 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 14 (19391404) , 9987-10002
Abstract
Change detection methods for optical remote sensing images play an important role in environmental resource management. Although recent methods based on deep learning demonstrate incredible ability by constructing networks, first, extracting bitemporal features in a separate manner; second, fusing bitemporal images before forwarding them into the single-level network. Both severely neglect the effect of spatial-temporal feature correlation between bitemporal images. In addition, most existing methods represent multiscale feature pairs in a layer-wise manner like ResNet, failing to consider the inner multilevel structure. In this work, we propose a new siamese change detection feature encoder backbone named cross-siamese Res2Net (CSRes2Net), by establishing crossed and hierarchical residual-like connections within one single residual block. The CSRes2Net represents dual features in a fine-grained manner and fully leads to the flow of bitemporal features. In addition, recent learning-based methods designed some spatial-temporal relation modules to capture the pixel-level pairwise relationship and channel dependency based on self-attention mechanism, but they only consider spatial and channel dimension corrections separately with excessive parameters. So we propose a lightweight cross spatial-channel triplet attention module to capture cross-dimensional long-range relationship between triplet combinations: channel with height, channel with width, channel with channel. Finally, we propose a hierarchical-split block for generating multiscale feature representations in a coarse-to-fine fashion. The experiments results on LEVIR-CD and season-varying change detection dataset outperform most state-of-the-art models.Keywords
Funding Information
- Shenzhen Science and Technology Program (KQTD20190929172704911)
This publication has 51 references indexed in Scilit:
- When Deep Learning Meets Metric Learning: Remote Sensing Image Scene Classification via Learning Discriminative CNNsIEEE Transactions on Geoscience and Remote Sensing, 2018
- Generative Adversarial Networks for Change Detection in Multispectral ImageryIEEE Geoscience and Remote Sensing Letters, 2017
- Change Detection Based on Deep Siamese Convolutional Network for Optical Aerial ImagesIEEE Geoscience and Remote Sensing Letters, 2017
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- A Deep Convolutional Coupling Network for Change Detection Based on Heterogeneous Optical and Radar ImagesIEEE Transactions on Neural Networks and Learning Systems, 2016
- Deep Residual Learning for Image Recognition2016
- Invariant multi-scale descriptor for shape representation, matching and retrievalComputer Vision and Image Understanding, 2016
- Semantic Annotation of High-Resolution Satellite Images via Weakly Supervised LearningIEEE Transactions on Geoscience and Remote Sensing, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015