AEFusion: A multi-scale fusion network combining Axial attention and Entropy feature Aggregation for infrared and visible images
AEFusion: A multi-scale fusion network combining Axial attention and Entropy feature Aggregation for infrared and visible images
复制标题
AEFusion：结合轴向注意力和熵特征聚合的多尺度融合网络，适用于红外和可见光图像
DOI：
10.1016/j.asoc.2022.109857
复制
发表时间：
2022-12-13
影响因子：
8.7
通讯作者：
Huang, Jie
中科院分区：
文献类型：
--
作者：
Li, Bicao;Lu, Jiaxi;Huang, Jie
图像融合的目的是生成一幅包含更多互补信息的图像。现有的图像融合方法存在细节信息丢失、伪影和/或不一致等问题。为了缓解这些问题，本文提出了一种结合Axial-attention的特征提取网络，该网络在提取多尺度特征的同时，能够捕获长距离的语义信息，具有更强的特征表示能力。同样地，现有的融合策略也遭受细节损失。为了解决这个问题，提出了一种新的融合策略，其中一个新的注意力机制，通过应用熵特征聚合边缘和细节特征。同时，设计了一种新的损失函数来约束网络。为了验证该方法的有效性，在公开数据集上进行了验证实验。与其他融合方法相比，实验结果表明，该方法在主观和客观评价方面都具有先进的优势。此外，消融研究说明了所提出的方法的优越性。(c)2022由Elsevier B. V.出版
The purpose of image fusion is to generate an image that contains more complementary information. Existing image fusion methods suffer from loss of detail information, artifacts and/or inconsistencies. To alleviate these problems, we propose a feature extraction network combining with Axial-attention, which can capture long-range semantic information while extracting multi-scale features and thus has stronger feature representation capabilities. Likewise, existing fusion strategies also suffer from loss of details. To solve this problem, a new fusion strategy is proposed, where a novel attention mechanism is constructed by applying entropy features to aggregate edge and detail features. At the same time, a new loss function is designed to constrain the network. To validate the efficiency of the proposed method, validation experiments are performed on public datasets. Compared with other fusion methods, the experimental results of the proposed method demonstrate state-of-the-art advantages in both subjective and objective evaluations. Furthermore, ablation studies illustrate the superiority of the proposed method. (c) 2022 Published by Elsevier B.V.