Semantic Segmentation-Driven Knowledge Distillation-Based Infrared Visible Image Fusion Framework
The goal of infrared and visible image fusion is to generate a fused image that integrates both prominent targets and fine textures. However, many existing fusion algorithms overly emphasize visual quality and traditional statistical evaluation metrics while neglecting the requirements of real-world...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10982250/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850271555752296448 |
|---|---|
| author | Xingshuo Wang |
| author_facet | Xingshuo Wang |
| author_sort | Xingshuo Wang |
| collection | DOAJ |
| description | The goal of infrared and visible image fusion is to generate a fused image that integrates both prominent targets and fine textures. However, many existing fusion algorithms overly emphasize visual quality and traditional statistical evaluation metrics while neglecting the requirements of real-world applications, especially in high-level vision tasks. To address this issue, this paper proposes a semantic segmentation-driven image fusion framework based on knowledge distillation. By incorporating a distributed structure of teacher and student networks, the framework leverages knowledge distillation to reduce network complexity, ensuring that the fused images are not only visually enhanced but also well-suited for downstream high-level vision tasks. Additionally, the introduction of two discriminators further optimizes the overall quality of the fused images, while the integration of a semantic segmentation module ensures that the fused images provide valuable support for advanced vision tasks. To enhance both fusion performance and segmentation capability, this paper proposes a joint training strategy that enables the fusion and segmentation networks to mutually improve during training. Experimental results on three public datasets demonstrate that the proposed method outperforms nine state-of-the-art fusion approaches in terms of visual quality, evaluation metrics, and semantic segmentation performance. Finally, ablation studies on the segmentation network further validate the effectiveness of the proposed method. |
| format | Article |
| id | doaj-art-6334c1e161884ecb9ab37c09de79fa4a |
| institution | OA Journals |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-6334c1e161884ecb9ab37c09de79fa4a2025-08-20T01:52:12ZengIEEEIEEE Access2169-35362025-01-0113834088342510.1109/ACCESS.2025.356643610982250Semantic Segmentation-Driven Knowledge Distillation-Based Infrared Visible Image Fusion FrameworkXingshuo Wang0https://orcid.org/0009-0007-8923-280XSchool of Information Science and Engineering, Shandong Normal University, Jinan, Shandong, ChinaThe goal of infrared and visible image fusion is to generate a fused image that integrates both prominent targets and fine textures. However, many existing fusion algorithms overly emphasize visual quality and traditional statistical evaluation metrics while neglecting the requirements of real-world applications, especially in high-level vision tasks. To address this issue, this paper proposes a semantic segmentation-driven image fusion framework based on knowledge distillation. By incorporating a distributed structure of teacher and student networks, the framework leverages knowledge distillation to reduce network complexity, ensuring that the fused images are not only visually enhanced but also well-suited for downstream high-level vision tasks. Additionally, the introduction of two discriminators further optimizes the overall quality of the fused images, while the integration of a semantic segmentation module ensures that the fused images provide valuable support for advanced vision tasks. To enhance both fusion performance and segmentation capability, this paper proposes a joint training strategy that enables the fusion and segmentation networks to mutually improve during training. Experimental results on three public datasets demonstrate that the proposed method outperforms nine state-of-the-art fusion approaches in terms of visual quality, evaluation metrics, and semantic segmentation performance. Finally, ablation studies on the segmentation network further validate the effectiveness of the proposed method.https://ieeexplore.ieee.org/document/10982250/Infrared and visible image fusionknowledge distillationdual discriminatorssemantic segmentation loss |
| spellingShingle | Xingshuo Wang Semantic Segmentation-Driven Knowledge Distillation-Based Infrared Visible Image Fusion Framework IEEE Access Infrared and visible image fusion knowledge distillation dual discriminators semantic segmentation loss |
| title | Semantic Segmentation-Driven Knowledge Distillation-Based Infrared Visible Image Fusion Framework |
| title_full | Semantic Segmentation-Driven Knowledge Distillation-Based Infrared Visible Image Fusion Framework |
| title_fullStr | Semantic Segmentation-Driven Knowledge Distillation-Based Infrared Visible Image Fusion Framework |
| title_full_unstemmed | Semantic Segmentation-Driven Knowledge Distillation-Based Infrared Visible Image Fusion Framework |
| title_short | Semantic Segmentation-Driven Knowledge Distillation-Based Infrared Visible Image Fusion Framework |
| title_sort | semantic segmentation driven knowledge distillation based infrared visible image fusion framework |
| topic | Infrared and visible image fusion knowledge distillation dual discriminators semantic segmentation loss |
| url | https://ieeexplore.ieee.org/document/10982250/ |
| work_keys_str_mv | AT xingshuowang semanticsegmentationdrivenknowledgedistillationbasedinfraredvisibleimagefusionframework |