Back to Search Start Over

Lightweight Infrared and Visible Image Fusion via Adaptive DenseNet with Knowledge Distillation

Authors :
Gao, Zongqing Zhao
Shaojing Su
Junyu Wei
Xiaozhong Tong
Weijia
Source :
Electronics; Volume 12; Issue 13; Pages: 2773
Publication Year :
2023
Publisher :
Multidisciplinary Digital Publishing Institute, 2023.

Abstract

The fusion of infrared and visible images produces a complementary image that captures both infrared radiation information and visible texture structure details using the respective sensors. However, the current deep-learning-based fusion approaches mainly tend to prioritize visual quality and statistical metrics, leading to an increased model complexity and weight parameter sizes. To address these challenges, we propose a novel dual-light fusion approach using adaptive DenseNet with knowledge distillation to learn and compress from pre-existing fusion models, which achieves the goals of model compression through the use of hyperparameters such as the width and depth of the model network. The effectiveness of our proposed approach is evaluated on a new dataset comprising three public datasets (MSRS, M3FD, and LLVIP), and both qualitative and quantitative experimental results show that the distillated adaptive DenseNet model effectively matches the original fusion models’ performance with smaller model weight parameters and shorter inference times.

Details

Language :
English
ISSN :
20799292
Database :
OpenAIRE
Journal :
Electronics; Volume 12; Issue 13; Pages: 2773
Accession number :
edsair.multidiscipl..9fbca847fe518a719c4cac9e99b5dd91
Full Text :
https://doi.org/10.3390/electronics12132773