2023
DOI: 10.3390/rs15174186
|View full text |Cite
|
Sign up to set email alerts
|

Bitemporal Remote Sensing Image Change Detection Network Based on Siamese-Attention Feedback Architecture

Hongyang Yin,
Chong Ma,
Liguo Weng
et al.

Abstract: Recently, deep learning-based change detection methods for bitemporal remote sensing images have achieved promising results based on fully convolutional neural networks. However, due to the inherent characteristics of convolutional neural networks, if the previous block fails to correctly segment the entire target, erroneous predictions might accumulate in the subsequent blocks, leading to incomplete change detection results in terms of structure. To address this issue, we propose a bitemporal remote sensing i… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2024
2024
2024
2024

Publication Types

Select...
4
1

Relationship

1
4

Authors

Journals

citations
Cited by 5 publications
(2 citation statements)
references
References 60 publications
0
2
0
Order By: Relevance
“…The coarse-to-fine boundary refinement network (CBR-Net) [44] can accurately extract building footprints from remote-sensing imagery. A bitemporal remote-sensing image change detection network based on a Siamese-attention feedback architecture, referred to as SAFNet [45], a global semantic module (GSM) on the encoder network, generates a low-resolution semantic change map to capture the changed objects, a temporal interaction module (TIM) and two auxiliary modules-the change feature extraction module (CFEM) and the feature refinement module (FRM)-to learn the fine boundaries of the changed target. The SAFNet algorithm exhibits state-of-the-art performance.…”
Section: Deep-learning Methods For Change Detection (Cd)mentioning
confidence: 99%
“…The coarse-to-fine boundary refinement network (CBR-Net) [44] can accurately extract building footprints from remote-sensing imagery. A bitemporal remote-sensing image change detection network based on a Siamese-attention feedback architecture, referred to as SAFNet [45], a global semantic module (GSM) on the encoder network, generates a low-resolution semantic change map to capture the changed objects, a temporal interaction module (TIM) and two auxiliary modules-the change feature extraction module (CFEM) and the feature refinement module (FRM)-to learn the fine boundaries of the changed target. The SAFNet algorithm exhibits state-of-the-art performance.…”
Section: Deep-learning Methods For Change Detection (Cd)mentioning
confidence: 99%
“…Based on the improved decoder-encoder structure of Unet++_MSOF and SNUNet [42], IFNet uses channel attention and spatial attention to optimize the feature weight distribution in the process of multi-scale skip connections. SAGNet and SAFNet [43] add a bi-temporal interaction layer between the encoding layers to communicate the semantic information of the twin branches. Secondly, there are models combining transformers and self-attention mechanisms, such as STANet, which models spatio-temporal relationships through multi-scale pooling and self-attention mechanisms.…”
Section: Comparative Experiments On Different Datasetsmentioning
confidence: 99%