SwinSUNet: Pure Transformer Network for Remote Sensing Image Change Detection

By Cui Zhang, Liejun Wang, Shuli Cheng, Yongming Li. IEEE Transactions on Geoscience and Remote Sensing, 2022

478 citations recorded by the source corpus.

Convolutional neural network (CNN) can extract effective semantic features, so it was widely used for remote sensing image change detection (CD) in the latest years. CNN has acquired great achievements in the field of CD, but due to the intrinsic locality of convolution operation, it could not capture global information in space-time. The Transformer was proposed in recent years and it can effectively extract global information, so it was used to solve computer vision (CV) tasks and achieved amazing success. In this paper, we design a pure Transformer network with siamese U-shaped structure to solve CD problems, and name it SwinSUNet. SwinSUNet contains encoder, fusion and decoder, and all of them use Swin Transformer blocks as basic units. Encoder has a siamese structure based on hierarchical Swin Transformer, so encoder can process bi-temporal images in parallel and extract their multi-scale features. Fusion is mainly responsible for the merge operation of the bi-temporal features generated by encoder. Like encoder, decoder also based on hierarchical Swin Transformer. Different from encoder, decoder uses up-sampling and merging (UM) block and Swin Transformer blocks to recover the details of the change information. The encoder uses patch merging and Swin Transformer blocks to generate effective semantic features. After the sequential process of these three modules, SwinSUNet will output the change maps. We did expensive experiments on four CD datasets, in these experiments SwinSUNet achieved better results than other related methods.

Subfields: Atmospheric Science, Media Technology

View Paper: https://www.semanticscholar.org/paper/f7c974321aa689102536228efcbcde3166acf1c9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

In Media Technology

Citations in the corpus

RS-Mamba for Large Remote Sensing Image Dense Prediction (2024, methodology): “In recent years, deep learning models based on transformers [7] have been widely applied to VHR remote sensing dense prediction tasks [8], [9], [10], [11].”
ChangeMamba: Remote Sensing Change Detection With Spatiotemporal State Space Model (2024, methodology): “On the Transformer front, we compare against ChangeFormer (versions 1 to 4) [22], BIT (with ResNet-18 to ResNet-101 as the backbone for feature extraction) [20], TransUNetCD [25], and SwinSUNet [24].”
Change Detection on Remote Sensing Images Using Dual-Branch Multilevel Intertemporal Network (2023, methodology): “Similarly, Zhang et al. [27] construct a pure Swin-transformer with a Siamese U-shaped structure for the CD task, which uses utmost exaggerated 32 Swin-transformer blocks.”
Large Selective Kernel Network for Remote Sensing Object Detection (2023, methodology): “Transformer-based [54] models, such as the Vision Transformer (ViT) [14, 49, 55, 11, 1], Swin transformer [36, 22, 63, 76, 47] and PVT [57] have gained popularity in computer vision due to their effectiveness in image recognition tasks.”