GTMFuse: Group-attention transformer-driven multiscale dense feature-enhanced network for infrared and visible image fusion

Mei, Liye; Hu, Xinglong; Ye, Zhaoyi; Tang, Linfeng; Wang, Ying; Li, Di; Liu, Yan; Hao, Xin; Lei, Cheng; Xu, Chuan; Yang, Wei

doi:10.1016/j.knosys.2024.111658

Cited by 12 publications

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The structure of the SPFM is illustrated in Figure 4. Inspired by [29][30][31], the SPFM first utilized the salient semantic map as prior knowledge to weight the input information, and then employed self-attention to achieve context awareness, guiding the model to perceive the spatial distribution of salient objects. Through this process, SPFM was able to allocate weights for different regions of the image, injecting additional semantic information into the region of salient targets on the input feature map, and preserving this crucial information as much as possible.…”

Section: Semantic Perception Fusion Module (Spfm)mentioning

confidence: 99%

Global Semantic-Sense Aggregation Network for Salient Object Detection in Remote Sensing Images

Li,

Chen,

Yang

et al. 2024

Entropy

Self Cite

View full text Add to dashboard Cite

Salient object detection (SOD) aims to accurately identify significant geographical objects in remote sensing images (RSI), providing reliable support and guidance for extensive geographical information analyses and decisions. However, SOD in RSI faces numerous challenges, including shadow interference, inter-class feature confusion, as well as unclear target edge contours. Therefore, we designed an effective Global Semantic-aware Aggregation Network (GSANet) to aggregate salient information in RSI. GSANet computes the information entropy of different regions, prioritizing areas with high information entropy as potential target regions, thereby achieving precise localization and semantic understanding of salient objects in remote sensing imagery. Specifically, we proposed a Semantic Detail Embedding Module (SDEM), which explores the potential connections among multi-level features, adaptively fusing shallow texture details with deep semantic features, efficiently aggregating the information entropy of salient regions, enhancing information content of salient targets. Additionally, we proposed a Semantic Perception Fusion Module (SPFM) to analyze map relationships between contextual information and local details, enhancing the perceptual capability for salient objects while suppressing irrelevant information entropy, thereby addressing the semantic dilution issue of salient objects during the up-sampling process. The experimental results on two publicly available datasets, ORSSD and EORSSD, demonstrated the outstanding performance of our method. The method achieved 93.91% Sα, 98.36% Eξ, and 89.37% Fβ on the EORSSD dataset.

show abstract

Section: Semantic Perception Fusion Module (Spfm)mentioning

confidence: 99%