计算机科学
人工智能
发电机(电路理论)
公制(单位)
编码器
特征(语言学)
模式识别(心理学)
图像融合
特征学习
深度学习
特征提取
代表(政治)
光学(聚焦)
计算机视觉
图像(数学)
运营管理
法学
功率(物理)
经济
语言学
哲学
物理
光学
政治学
操作系统
政治
量子力学
作者
Zhishe Wang,Wenyu Shao,Yanlin Chen,Jiawei Xu,Xiaoqin Zhang
标识
DOI:10.1109/tmm.2022.3228685
摘要
The existing generative adversarial fusion methods generally concatenate source images or deep features, and extract local features through convolutional operations without considering their global characteristics, which tends to produce a limited fusion performance. Toward this end, we propose a novel interactive compensatory attention fusion network, termed ICAFusion. In particular, in the generator, we construct a multi-level encoder-decoder network with a triple path, and design infrared and visible paths to provide additional intensity and gradient information for the concatenating path. Moreover, we develop the interactive and compensatory attention modules to communicate their pathwise information, and model their long-range dependencies through a cascading channel-spatial model. The generated attention maps can more focus on infrared target perception and visible detail characterization, and are used to reconstruct the fusion image. Therefore, the generator takes full advantage of local and global features to further increase the representation ability of feature extraction and feature reconstruction. Extensive experiments illustrate that our ICAFusion obtains superior fusion performance and better generalization ability, which precedes other advanced methods in the subjective visual description and objective metric evaluation. Our codes will be public at https://github.com/Zhishe-Wang/ICAFusion .
科研通智能强力驱动
Strongly Powered by AbleSci AI