Progressive Modality-Adaptive Interactive Network for Multi-Modality Image Fusion
Authors: Chaowei Huang, Yaru Su, Huangbiao Xu, Xiao Ke
IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on benchmark datasets demonstrate that Po MAI surpasses state-of-the-art methods in fusion quality and excels in downstream tasks. |
| Researcher Affiliation | Academia | Chaowei Huang1,2, Yaru Su1,2, Huangbiao Xu1,2, Xiao Ke1,2 1Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing, College of Computer and Data Science, Fuzhou University, Fuzhou 350116, China 2Engineering Research Center of Big Data Intelligence, Ministry of Education, Fuzhou 350116, China EMAIL, EMAIL, EMAIL, EMAIL |
| Pseudocode | No | The paper describes the model architecture and mathematical formulations (e.g., Eq. 1-18) but does not provide structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not contain any explicit statement about releasing source code or a link to a code repository for the described methodology. |
| Open Datasets | Yes | We conduct IVF experiments on four popular datasets: TNO [Toet and Hogervorst, 2012], Road Scene [Xu et al., 2020], M3FD [Liu et al., 2022], and MSRS [Tang et al., 2022]... We perform MIF experiments using 50 image pairs from the Harvard Medical dataset [Johnson and Becker, 2005]. |
| Dataset Splits | Yes | Our proposed method, Po MAI, is trained on the MSRS training set (1083 pairs) and tested on TNO (20 pairs), Road Scene (70 pairs), M3FD (100 pairs), and the MSRS test set (361 pairs)... The dataset is split into training, validation, and test sets with an 8:1:1 ratio. |
| Hardware Specification | Yes | Our experiments are implemented with the Pytorch framework and on a machine with four NVIDIA Tesla P100 GPUs. |
| Software Dependencies | No | The paper mentions 'Pytorch framework' but does not specify a version number or any other software dependencies with their versions. |
| Experiment Setup | Yes | The training process is structured into two phases: the first phase comprises 80 epochs, followed by the second phase with 20 epochs, both utilizing a batch size of 16. The Adam optimizer is employed to update the parameters of each module, with an initial learning rate of 1 × 10−4 that decreases by a factor of 0.5 every 20 epochs. In Eq. 14, the values of α1, α2, α3, and α4 are set to 5, 1, 1, and 10. |