相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article
Computer Science, Artificial Intelligence
Andrea Codegoni et al.
Summary: TinyCD is a lightweight and effective change detection model designed to be faster and smaller than current state-of-the-art models, outperforming them on different datasets by using Siamese U-Net architecture and a novel feature mixing strategy.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Geochemistry & Geophysics
Sheng Fang et al.
Summary: This letter proposes a densely connected siamese network (SNUNet-CD) for change detection, which alleviates the loss of localization information in deep layers and introduces ECAM for deep supervision. Experimental results show that the method achieves a better tradeoff between accuracy and calculation amount compared to other state-of-the-art change detection methods.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Hao Chen et al.
Summary: This study introduces a bitemporal image transformer (BIT) for efficient and effective change detection by modeling contexts in the spatial-temporal domain. The BIT model demonstrates superior performance and efficiency on three CD datasets, significantly outperforming the purely convolutional baseline model with lower computational costs.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Xin Wu et al.
Summary: This paper proposes a new framework for multimodal remote sensing data classification, using deep learning and a cross-channel reconstruction module to learn compact fusion representations of different data sources. Extensive experiments on two multimodal RS datasets demonstrate the effectiveness and superiority of the proposed method.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Proceedings Paper
Geosciences, Multidisciplinary
Biyuan Liu et al.
Summary: This paper proposes an extremely lightweight Siamese network (LSNet) for remote sensing image change detection, which greatly compresses parameters and computation amount by using depthwise separable atrous convolution and removing redundant dense connections.
2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022)
(2022)
Proceedings Paper
Geosciences, Multidisciplinary
Wele Gedara Chaminda Bandara et al.
Summary: This paper presents a transformer-based Siamese network architecture (ChangeFormer) for Change Detection from a pair of co-registered remote sensing images. By unifying hierarchically structured transformer encoder with MLP decoder in a Siamese network architecture, it efficiently renders multi-scale long-range details required for accurate change detection. Experimental results show that the proposed ChangeFormer architecture achieves better performance than previous methods on two change detection datasets.
2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022)
(2022)
Article
Geochemistry & Geophysics
Jiawei Jiang et al.
Summary: Detection of forest changes is crucial for restoring forest land resources and ensuring standardized government management. However, seasonal factors often lead to a high number of false change detections. To address this issue, we propose a model called Forest-CD, which utilizes an encoder-decoder structure and background information to suppress pseudo changes. Experimental results demonstrate that Forest-CD achieves a higher F1-Score compared to other models and accurately captures the boundaries of forest changes.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Yi Liu et al.
Summary: The proposed dual-task constrained deep Siamese convolutional network (DTCDSCN) model achieves both change detection and semantic segmentation simultaneously, improving feature extraction and representation to address the issue of lack of discriminative features in change detection. Experimental results demonstrate state-of-the-art performance on the WHU building data set, showcasing the effectiveness of the proposed method.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2021)
Article
Geochemistry & Geophysics
Danfeng Hong et al.
Summary: This study introduces a general multimodal deep learning (MDL) framework for the classification and identification challenges in geoscience and remote sensing. By investigating a special case of multi-modality learning (MML), the study presents five fusion strategies and demonstrates how to train deep networks and build network architectures effectively. Experimental results on two different multimodal RS data sets confirm the efficiency and advantages of the proposed MDL framework.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Computer Science, Artificial Intelligence
Tianyi Wu et al.
Summary: The research presents a lightweight and efficient semantic segmentation network CGNet, which captures contextual information in all stages of the network through context-guided technology, designed specifically to increase segmentation accuracy and reduce memory usage. Experimental results show that CGNet achieves good performance on the Cityscapes dataset.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Environmental Sciences
Hao Chen et al.
Article
Remote Sensing
K Nackaerts et al.
INTERNATIONAL JOURNAL OF REMOTE SENSING
(2005)