TY  - JOUR
AU  - Qiu, Weitao
AU  - Zhao, Wenda
AU  - Wang, Haipeng
PY  - 2025
DA  - 2025/09/21
TI  - Self-supervised Segmentation Feature Alignment for Infrared and Visible Image Fusion
JO  - Chinese Journal of Information Fusion
T2  - Chinese Journal of Information Fusion
JF  - Chinese Journal of Information Fusion
VL  - 2
IS  - 3
SP  - 223
EP  - 236
DO  - 10.62762/CJIF.2025.822280
UR  - https://www.icck.org/article/abs/CJIF.2025.822280
KW  - image fusion
KW  - self-supervised segmentation feature alignment
KW  - feature interaction
KW  - deep learning
AB  - Existing deep learning-based methods for infrared and visible image fusion typically operate independently of other high-level vision tasks, overlooking the potential benefits these tasks could offer. For instance, semantic features from image segmentation could enrich the fusion results by providing detailed target information. However, segmentation focuses on target-level semantic feature information (e.g., object categories), while fusion focuses more on pixel-level detail feature information (e.g., local textures), creating a feature representation gap. To address this challenge, we propose a self-supervised segmentation feature alignment fusion network (SegFANet), which aligns target-level semantic features from segmentation tasks with pixel-level fusion features through self-supervised learning, thereby bridging the feature gap between the two tasks and improving the quality of image fusion. Extensive experiments on the WHU and Potsdam datasets show our method's effectiveness, outperforming the state-of-the-art methods.
SN  - 2998-3371
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Qiu2025Selfsuperv,
  author = {Weitao Qiu and Wenda Zhao and Haipeng Wang},
  title = {Self-supervised Segmentation Feature Alignment for Infrared and Visible Image Fusion},
  journal = {Chinese Journal of Information Fusion},
  year = {2025},
  volume = {2},
  number = {3},
  pages = {223-236},
  doi = {10.62762/CJIF.2025.822280},
  url = {https://www.icck.org/article/abs/CJIF.2025.822280},
  abstract = {Existing deep learning-based methods for infrared and visible image fusion typically operate independently of other high-level vision tasks, overlooking the potential benefits these tasks could offer. For instance, semantic features from image segmentation could enrich the fusion results by providing detailed target information. However, segmentation focuses on target-level semantic feature information (e.g., object categories), while fusion focuses more on pixel-level detail feature information (e.g., local textures), creating a feature representation gap. To address this challenge, we propose a self-supervised segmentation feature alignment fusion network (SegFANet), which aligns target-level semantic features from segmentation tasks with pixel-level fusion features through self-supervised learning, thereby bridging the feature gap between the two tasks and improving the quality of image fusion. Extensive experiments on the WHU and Potsdam datasets show our method's effectiveness, outperforming the state-of-the-art methods.},
  keywords = {image fusion, self-supervised segmentation feature alignment, feature interaction, deep learning},
  issn = {2998-3371},
  publisher = {Institute of Central Computation and Knowledge}
}