MASNet:Improve Performance of Siamese Networks with Mutual-attention for Remote Sensing Change Detection Tasks
Not on the map. Why?
Abstract (arXiv)
Siamese networks are widely used for remote sensing change detection tasks. A vanilla siamese network has two identical feature extraction branches which share weights, these two branches work independently and the feature maps are not fused until about to be sent to a decoder head. However we find that it is critical to exchange information between two feature extraction branches at early stage for change detection task. In this work we present Mutual-Attention Siamese Network (MASNet), a general siamese network with mutual-attention plug-in, so to exchange information between the two feature extraction branches. We show that our modification improve the performance of siamese networks on multi change detection datasets, and it works for both convolutional neural network and visual transformer.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 19 of its 31 references that are in the map. First posted on arXiv 6 Jun 2022.
Builds on
19 of 31 references.
References · 19
- 2017Attention Is All You Needcited by 60,361
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
- 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
- 2017Non-local Neural Networkscited by 2,293
- 2018Dual Attention Network for Scene Segmentationcited by 1,003
- 2013Network In Networkcited by 605
- 2018Fully Convolutional Siamese Networks for Change Detectioncited by 306
- 2019High-Resolution Representations for Labeling Pixels and Regionscited by 211
- 2019Building Change Detection for Remote Sensing Images Using a Dual Task Constrained Deep Siamese Convolutional Network Modelcited by 85
7 more
- 2020DASNet: Dual attentive fully convolutional siamese networks for change detection of high resolution satellite imagescited by 75
- 2021Change is Everywhere: Single-Temporal Supervised Object Change Detection in Remote Sensing Imagerycited by 64
- 2019Region Mutual Information Loss for Semantic Segmentationcited by 49
- 2021FCCDN: Feature Constraint Network for VHR Image Change Detectioncited by 25
- 2020Looking for change? Roll the Dice and demand Attentioncited by 15
- 2021Urban Change Detection by Fully Convolutional Siamese Concatenate Network with Attentioncited by 1
- 2021Towards Deep and Efficient: A Deep Siamese Self-Attention Fully Efficient Convolutional Network for Change Detection in VHR Imagescited by 1
Built on by
Citing papers per year: 2023: 1.
1 paper.