A Convolutional Sparse Representations Integration Strategy Based on Self-Attention Genetic Programming for Multimodal Image Fusion

Created by W.Langdon from gp-bibliography.bib Revision:1.8620

@InProceedings{DBLP:conf/cec/LuoLJ25,

• author = "Yi Luo and Chang Liu and Dong Ji",
• title = "A Convolutional Sparse Representations Integration Strategy Based on Self-Attention Genetic Programming for Multimodal Image Fusion",
• booktitle = "2025 IEEE Congress on Evolutionary Computation (CEC)",
• year = "2025",
• editor = "Yaochu Jin and Thomas Baeck",
• address = "Hangzhou, China",
• month = "8-12 " # jun,
• publisher = "IEEE",
• keywords = "genetic algorithms, genetic programming, Convolutional codes, Measurement, Visualization, Correlation, Feature extraction, Encoding, Image fusion, Optimization, Biomedical imaging, multimodal image fusion, self-attention, convolutional sparse coding",
• isbn13 = "979-8-3315-3432-5",
• timestamp = "Mon, 30 Jun 2025 01:00:00 +0200",
• biburl = "https://dblp.org/rec/conf/cec/LuoLJ25.bib",
• bibsource = "dblp computer science bibliography, https://dblp.org",
• URL = "https://doi.org/10.1109/CEC65147.2025.11043003",
• DOI = "10.1109/CEC65147.2025.11043003",
• abstract = "Multimodal image fusion (MIF) seeks to amalgamate complementary information from various image modalities, offering a more comprehensive and accurate representation of data. Convolutional sparse coding (CSC) based methods have demonstrated effectiveness in this domain. However, they encounter difficulties in adaptively discerning and leveraging cross-modality feature correlations, which essentially presents a multi-objective optimisation challenge, such as maximizing information retention while minimizing feature distortion. To address this issue, we introduce a self-attention based multi-objective genetic programming (SA-MOGP) method. SA-MOGP frames the quest for an optimal fusion strategy as a multi-objective optimisation problem. By integrating the self-attention mechanism into strongly typed genetic programming (STGP), it enables efficient exploration of associations between sparse features across different modalities. Our approach is structured in three hierarchical layers. The feature extraction (FE) layer automatically generates Q, K, V sub-trees according to a predefined function set. These are then input into the self-attention (SA) layer for computation. Finally, the output layer estimates the fusion weights. We use the NSGAII framwork to solve this multi-objective problem, aiming for Pareto front solutions. Experiments on infrared-visible and medical image datasets attest to the superior performance of the SAGP method in multimodal image fusion.",
• notes = "also known as \cite{luo:2025:CEC} \cite{11043003}",

}

Genetic Programming entries for Yi Luo Chang Liu Dong Ji

Citations