SiamixFormer: a fully-transformer Siamese network with temporal Fusion for accurate building detection and change detection in bi-temporal remote sensing images

Mohammadian, Amir; Ghaderi, Foad

doi:10.1080/01431161.2023.2225228

Cited by 11 publications

(6 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compared our method with FC-EF, FC-Siam-conc, FC-Siam-diff [19], STANet [31], BIT [32], L-UNet [30], DSIFN [33], SNUNet [28], RDP-Net [20], Changer [47], SiamixFormer [54], BAN [45], and LightCDNet [65]. These methods represent deep learning-based approaches in the field of CD.…”

Section: Comparison With Sota Methodsmentioning

confidence: 99%

See 1 more Smart Citation

RDP-Net: Region Detail Preserving Network for Change Detection

Chen

Yang

et al. 2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Change detection (CD) in remote sensing imagery is a crucial task with applications in environmental monitoring, urban development, and disaster management. CD involves utilizing bi-temporal images to identify changes over time. The bi-temporal spatial relationships between features at the same location at different times play a key role in this process. However, existing change detection networks often do not fully leverage these spatial relationships during bi-temporal feature extraction and fusion. In this work, we propose SRC-Net: a bitemporal spatial relationship concerned network for CD. The proposed SRC-Net includes a Perception and Interaction Module that incorporates spatial relationships and establishes a crossbranch perception mechanism to enhance the precision and robustness of feature extraction. Additionally, a Patch-Mode joint Feature Fusion Module is introduced to address information loss in current methods. It considers different change modes and concerns about spatial relationships, resulting in more expressive fusion features. Furthermore, we construct a novel network using these two relationship concerned modules and conducted experiments on the LEVIR-CD and WHU Building datasets. The experimental results demonstrate that our network outperforms state-of-the-art (SOTA) methods while maintaining a modest parameter count. We believe our approach sets a new paradigm for change detection and will inspire further advancements in the field. The code and models are publicly available at https://github.com/Chnja/SRCNet.

show abstract

Section: Comparison With Sota Methodsmentioning

confidence: 99%

“…These modules neglect to consider the spatial relationships among bi-temporal data. Mohammadian et al [54] used the Key, Query, and Value matrices from the self-attention mechanism within Transformer to fuse bitemporal features and proposed SiamxFormer. The fusion result is obtained by a temporal transformer.…”

Section: Feature Fusionmentioning

confidence: 99%

RDP-Net: Region Detail Preserving Network for Change Detection

Chen

Yang

et al. 2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…To address this challenge and achieve better representation capabilities of deep features, designing deeper and more complex feature extraction networks has gotten significant attention as a primary research focus. Many researchers have put forward several enhanced models to achieve more discriminative feature representations, such as combining Generative Adversarial Networks (GAN) [38][39][40] or Recurrent Neural Networks (RNN) [41,42], or using feature extraction models based on the Transformer architecture [43][44][45] to expand the receptive field. Some studies focus on the effective utilization of features, such as using spatial or channel attention mechanisms [30][31][32]36,46] or employing multi-scale feature fusion for feature enhancement [25,29,[47][48][49].…”

Section: Introductionmentioning

confidence: 99%

MFSFNet: Multi-Scale Feature Subtraction Fusion Network for Remote Sensing Image Change Detection

Huang

You

2023

Remote Sensing

View full text Add to dashboard Cite

Change detection plays a crucial role in remote sensing by identifying surface modifications between two sets of temporal remote sensing images. Recent advancements in deep learning techniques have yielded significant achievements in this field. However, there are still some challenges: (1) Existing change feature fusion methods often introduce redundant information. (2) The complexity of network structures leads to a large number of parameters and difficulties in model training. To overcome these challenges, this paper proposes a Multi-Scale Feature Subtraction Fusion Network (MFSF-Net). It comprises two primary modules: the Multi-scale Feature Subtraction Fusion (MFSF) module and the Feature Deep Supervision (FDS) module. MFSF enhances change features and reduces redundant pseudo-change features. FDS provides additional supervision on different scales of change features in the decoder, improving the training efficiency performance of the network. Additionally, to address the problem of imbalanced samples, the Dice loss strategy is introduced as a means to mitigate this issue. Through comprehensive experiments, MFSF-Net achieves an F1 score of 91.15% and 95.64% on LEVIR-CD and CDD benchmark datasets, respectively, outperforming six state-of-the-art algorithms. Moreover, it attains an improved balance between model complexity and performance, showcasing the efficacy of the proposed approach.

show abstract

“…In recent years, the leveraging of open-source datasets [7][8][9][10][11][12][13][14][15][16] in the field of BCD research has resulted in a surge of state-of-the-art (SOTA) methods. These methods predominantly rely on deep convolutional neural networks (DCNNs) [17][18][19][20][21][22][23][24] and transformer models [25][26][27][28]. They approach BCD as a high-stakes prediction task, producing pixel-level outputs.…”

Section: Introductionmentioning

confidence: 99%

Detection of Changes in Buildings in Remote Sensing Images via Self-Supervised Contrastive Pre-Training and Historical Geographic Information System Vector Maps

Feng,

Guan,

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

The detection of building changes (hereafter ‘building change detection’, BCD) is a critical issue in remote sensing analysis. Accurate BCD faces challenges, such as complex scenes, radiometric differences between bi-temporal images, and a shortage of labelled samples. Traditional supervised deep learning requires abundant labelled data, which is expensive to obtain for BCD. By contrast, there is ample unlabelled remote sensing imagery available. Self-supervised learning (SSL) offers a solution, allowing learning from unlabelled data without explicit labels. Inspired by SSL, we employed the SimSiam algorithm to acquire domain-specific knowledge from remote sensing data. Then, these well-initialised weight parameters were transferred to BCD tasks, achieving optimal accuracy. A novel framework for BCD was developed using self-supervised contrastive pre-training and historical geographic information system (GIS) vector maps (HGVMs). We introduced the improved MS-ResUNet network for the extraction of buildings from new temporal satellite images, incorporating multi-scale pyramid image inputs and multi-layer attention modules. In addition, we pioneered a novel spatial analysis rule for detecting changes in building vectors in bi-temporal images. This rule enabled automatic BCD by harnessing domain knowledge from HGVMs and building upon the spatial analysis of building vectors in bi-temporal images. We applied this method to two extensive datasets in Liuzhou, China, to assess its effectiveness in both urban and suburban areas. The experimental results demonstrated that our proposed approach offers a competitive quantitative and qualitative performance, surpassing existing state-of-the-art methods. Combining HGVMs and high-resolution remote sensing imagery from the corresponding years is useful for building updates.

show abstract

SiamixFormer: a fully-transformer Siamese network with temporal Fusion for accurate building detection and change detection in bi-temporal remote sensing images

Cited by 11 publications

References 27 publications

RDP-Net: Region Detail Preserving Network for Change Detection

RDP-Net: Region Detail Preserving Network for Change Detection

MFSFNet: Multi-Scale Feature Subtraction Fusion Network for Remote Sensing Image Change Detection

Detection of Changes in Buildings in Remote Sensing Images via Self-Supervised Contrastive Pre-Training and Historical Geographic Information System Vector Maps

Contact Info

Product

Resources

About