AAUNet: An Attention Augmented Convolution Based UNet for Change Detection in High Resolution Satellite Images

Patil, Parmeshwar; Holambe, Raghunath S.; Waghmare, L. M.

doi:10.1007/978-3-031-11346-8_36

Cited by 1 publication

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Table 4, DEF-Net achieves the best values in F 1 and S e , which indicates that our proposed method shows advantages in segmenting vascular pixels. AAUNet [26] achieves the best AUC, and it uses an enhanced convolution to replace the standard convolution, but the detail information is lost during this process, thus resulting in a lower S e . IterNet [27] uses multiple sub-UNet to build the model, resulting in feature redundancy, and its S e is only 0.7791.…”

Section: Quantitative Resultsmentioning

confidence: 99%

DEF-Net: A Dual-Encoder Fusion Network for Fundus Retinal Vessel Segmentation

Gao

Yang

et al. 2022

Electronics

View full text Add to dashboard Cite

The deterioration of numerous eye diseases is highly related to the fundus retinal structures, so the automatic retinal vessel segmentation serves as an essential stage for efficient detection of eye-related lesions in clinical practice. Segmentation methods based on encode-decode structures exhibit great potential in retinal vessel segmentation tasks, but have limited feature representation ability. In addition, they don’t effectively consider the information at multiple scales when performing feature fusion, resulting in low fusion efficiency. In this paper, a newly model, named DEF-Net, is designed to segment retinal vessels automatically, which consists of a dual-encoder unit and a decoder unit. Fused with recurrent network and convolution network, a dual-encoder unit is proposed, which builds a convolutional network branch to extract detailed features and a recurrent network branch to accumulate contextual features, and it could obtain richer features compared to the single convolution network structure. Furthermore, to exploit the useful information at multiple scales, a multi-scale fusion block used for facilitating feature fusion efficiency is designed. Extensive experiments have been undertaken to demonstrate the segmentation performance of our proposed DEF-Net.

show abstract

Section: Quantitative Resultsmentioning

confidence: 99%