TY - JOUR
T1 - TransY-Net
T2 - Learning Fully Transformer Networks for Change Detection of Remote Sensing Images
AU - Yan, Tianyu
AU - Wan, Zifu
AU - Zhang, Pingping
AU - Cheng, Gong
AU - Lu, Huchuan
N1 - Publisher Copyright:
© 1980-2012 IEEE.
PY - 2023
Y1 - 2023
N2 - In the remote sensing field, change detection (CD) aims to identify and localize the changed regions from dual-phase images over the same places. Recently, it has achieved great progress with the advances of deep learning. However, current methods generally deliver incomplete CD regions and irregular CD boundaries due to the limited representation ability of the extracted visual features. To relieve these issues, in this work we propose a novel transformer-based learning framework named TransY-Net for remote sensing image CD, which improves the feature extraction from a global view and combines multilevel visual features in a pyramid manner. More specifically, the proposed framework first uses the advantages of transformers in long-range dependency modeling. It can help learn more discriminative global-level features and obtain complete CD regions. Then, we introduce a novel pyramid structure to aggregate multilevel visual features from transformers for feature enhancement. The pyramid structure grafted with a progressive attention module (PAM) can improve the feature representation ability with additional interdependencies through spatial and channel attentions. Finally, to better train the whole framework, we use the deeply supervised learning with multiple boundary-aware loss functions. Extensive experiments demonstrate that our proposed method achieves a new state-of-the-art performance on four optical and two SAR image CD benchmarks. The source code is released at https://github.com/Drchip61/TransYNet.
AB - In the remote sensing field, change detection (CD) aims to identify and localize the changed regions from dual-phase images over the same places. Recently, it has achieved great progress with the advances of deep learning. However, current methods generally deliver incomplete CD regions and irregular CD boundaries due to the limited representation ability of the extracted visual features. To relieve these issues, in this work we propose a novel transformer-based learning framework named TransY-Net for remote sensing image CD, which improves the feature extraction from a global view and combines multilevel visual features in a pyramid manner. More specifically, the proposed framework first uses the advantages of transformers in long-range dependency modeling. It can help learn more discriminative global-level features and obtain complete CD regions. Then, we introduce a novel pyramid structure to aggregate multilevel visual features from transformers for feature enhancement. The pyramid structure grafted with a progressive attention module (PAM) can improve the feature representation ability with additional interdependencies through spatial and channel attentions. Finally, to better train the whole framework, we use the deeply supervised learning with multiple boundary-aware loss functions. Extensive experiments demonstrate that our proposed method achieves a new state-of-the-art performance on four optical and two SAR image CD benchmarks. The source code is released at https://github.com/Drchip61/TransYNet.
KW - Change detection (CD)
KW - deep learning
KW - progressive attention
KW - remote sensing image
KW - vision transformer
UR - http://www.scopus.com/inward/record.url?scp=85176303832&partnerID=8YFLogxK
U2 - 10.1109/TGRS.2023.3327253
DO - 10.1109/TGRS.2023.3327253
M3 - 文章
AN - SCOPUS:85176303832
SN - 0196-2892
VL - 61
SP - 1
EP - 12
JO - IEEE Transactions on Geoscience and Remote Sensing
JF - IEEE Transactions on Geoscience and Remote Sensing
M1 - 4410012
ER -