A Transformer-Based Siamese Network for Change Detection

Bandara, Wele Gedara Chaminda; Patel, Vishal M.

doi:10.1109/igarss46834.2022.9883686

Cited by 382 publications

(209 citation statements)

References 5 publications

Supporting

Mentioning

209

Contrasting

Order By: Relevance

“…Chen et al [57] presented a bi-temporal image transformer (BIT) for CD, which can efficiently model contexts and obtain semantic relationships. Bandara et al [58] utilized the hierarchical transformer encoder in a Siamese architecture for CD, which can capture multi-scale details. Zhang et al [59] designed a Siamese Ushaped pure transformer network (SwinSUNet) to get longterm global information in spacetime.…”

Section: Transformer-based Methods In CVmentioning

confidence: 99%

“…We compare the proposed CDENet with some existing methods. The comparison methods include: FC-EF [25], FC-Siam-conc [25], FC-Siam-diff [25], DSIFN [44], DTCDSCN [48], SNUNet [50], DSAMNet [51], BIT [57], and ChangeFormer [58].…”

Section: Comparative Experiments 1) Comparison Methodsmentioning

confidence: 99%

“…BIT [57] modeled the context relationships with the transformers, which can better identify the change regions. ChangeFormer [58] utilized the hierarchical transformer encoder in a Siamese architecture, which can capture multi-scale details.…”

Section: Comparative Experiments 1) Comparison Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Context and Difference Enhancement Network for Change Detection

Song

Dong

2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

At present, convolution neural networks have achieved good performance in remote sensing image change detection. However, due to the locality of convolution, these methods are difficult to capture the global context relationships among different-level features. To alleviate this issue, we propose a context and difference enhancement network (CDENet) for change detection, which can strongly model global context relationships and enhance the change difference. Specifically, our backbone is the dual TransUNet, which is based on U-Net and equipped with transformer block in the encoder. The dual TransUNet is used to extract bi-temporal features. Then, the features are encoded as the input sequence, which is conducive to modeling the global context. Moreover, we design the content difference enhancement module to process the dual features of each layer in the encoder. The designed module can increase the spatial attention of difference regions to enhance the change difference features. In the decoder, we adopt a simple crosslayer feature fusion to combine the upsampled features with the high-resolution features, which is used to generate more accurate results. Finally, we adopt a novel loss to supervise the accuracy of results in regions and pixels. The experiments on two public change detection datasets demonstrate that our CDENet has strong competitiveness and performs better than the state-ofthe-art methods.

show abstract

Section: Transformer-based Methods In CVmentioning

confidence: 99%

Section: Comparative Experiments 1) Comparison Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Context and Difference Enhancement Network for Change Detection

Song

Dong

2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…: mean squared error to solve the 3D CD task). Finally, an attention-based model (Vaswani et al, 2017) is under development as well, given the effectiveness of such family of models also for RS CD applications (Bandara and Patel, 2022). Moreover, we are already considering to integrate the dataset with new pairs of optical images, accompanied by the respective 2D and 3D change masks, on areas already identified and subjected to elevation variations.…”

Section: Dataset Descriptionmentioning

confidence: 99%

3dcd: A New Dataset for 2d and 3d Change Detection Using Deep Learning Techniques

Coletta

Marsocci

Ravanelli

2022

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Change detection is one of the main topics in Earth Observation, due to its wide range of applications, varying from urban development monitoring to natural disaster management. Most of the recently developed change detection methodologies rely on the use of deep learning algorithms. These kinds of algorithms are generally focused on generating two-dimensional (2D) change maps, thus they are only able to detect horizontal changes in land use/land cover, not considering nor returning any information on the corresponding elevation changes. Our work proposes a step forward, creating and sharing a dataset where two optical images acquired in different epochs are provided together with both the related 2D change maps containing land use/land cover variations and the three-dimensional (3D) maps containing elevation changes. Particularly, our aim is to provide a dataset useful to address and possibly solve the change detection task in 3D. Indeed, the proposed dataset, on the one hand, can empower a further development of 2D change detection algorithms, and, on the other hand, can allow to develop algorithms able to provide 3D change detection maps from two optical images captured in different epochs, without the need to rely directly on elevation data as input. The proposed dataset is publicly available at the following link: https://bit.ly/3wDdo41.

show abstract

“…Howerer, compact semantic tokens loses some useful high-level feature information and the decoded feature lacks low-level information such as texture and contour. Were et al [39] proposed Changeformer, which unifies hierarchically structured transformer encoder with Multi-Layer Perception (MLP) decoder in a Siamese network architecture to efficiently render multi-scale long-range details required for accurate CD. This architecture lacks convolution blocks to capture local features at high resolution stage.…”

Section: Introductionmentioning

confidence: 99%

STransUNet: A Siamese TransUNet-Based Remote Sensing Image Change Detection Network

Jian

Wang

Cheng

2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

In modern remote sensing image change detection (CD), convolution Neural Network (CNN), especially U-shaped structure (UNet), has achieved great success due to powerful discriminative ability. However, UNet-based CNN networks usually have limitations in modeling global dependencies due to intrinsic locality of convolution operations. Transformer has recently emerged as an alternative architecture for dense prediction tasks due to global self-attention mechanism. However, due to limitation of hardware resources, pure Transformer methods generally lack the ability to capture global information at a low level. Based on these existing problems, we propose STransUNet, which combines Transformer and UNet architecture. STransUNet can not only capture shallow detail features at an early stage, but also model global context in high-level feature. In addition, we design an efficient feature fusion module named Cross-Enhanced Adaptive Fusion(CEAF). Our model mainly consists of three parts: encoder, fusion module and decoder. The decoder is a CNN-Transformer hybrid structure. CNN extracts multi-level feature information. Transformer encodes tokenized sequence to capture global context. CEAF module cross-enhances and adaptively fuses bi-temporal features to enhance feature representation. In decoding stage, we introduce a Cascaded Upsampling decoder(CUP). CUP progressively aggregates lowlevel CNN features and high-level Transformer features to full resolution. On four public CD datasets, our STransUNet achieves better CD results than six state-of-the-art algorithms.

show abstract

A Transformer-Based Siamese Network for Change Detection

Cited by 382 publications

References 5 publications

Context and Difference Enhancement Network for Change Detection

Context and Difference Enhancement Network for Change Detection

3dcd: A New Dataset for 2d and 3d Change Detection Using Deep Learning Techniques

STransUNet: A Siamese TransUNet-Based Remote Sensing Image Change Detection Network

Contact Info

Product

Resources

About