Skip navigation
Please use this identifier to cite or link to this item: https://libeldoc.bsuir.by/handle/123456789/54446
Full metadata record
DC FieldValueLanguage
dc.contributor.authorImad Ali Shah-
dc.contributor.authorFahad Mumtaz Malik-
dc.contributor.authorMuhammad Waqas Ashraf-
dc.coverage.spatialМинскen_US
dc.date.accessioned2024-03-01T07:35:32Z-
dc.date.available2024-03-01T07:35:32Z-
dc.date.issued2023-
dc.identifier.citationImad Ali Shah. SFA-UNet: More Attention to Multi-Scale Contrast and Contextual Information in Infrared Small Object Segmentation / Imad Ali Shah, Fahad Mumtaz Malik, Muhammad Waqas Ashraf // Pattern Recognition and Information Processing (PRIP'2023) = Распознавание образов и обработка информации (2023) : Proceedings of the 16th International Conference, October 17–19, 2023, Minsk, Belarus / United Institute of Informatics Problems of the National Academy of Sciences of Belarus. – Minsk, 2023. – P. 147–152.en_US
dc.identifier.urihttps://libeldoc.bsuir.by/handle/123456789/54446-
dc.description.abstractComputer vision researchers have extensively worked on fundamental infrared visual recognition for the past few decades. Among various approaches, deep learning has emerged as the most promising candidate. However, Infrared Small Object Segmentation (ISOS) remains a major focus due to several challenges including: 1) the lack of effective utilization of local contrast and global contextual information; 2) the potential loss of small objects in deep models; and 3) the struggling to capture fine-grained details and ignore noise. To address these challenges, we propose a modified U-Net architecture, named SFA-UNet, by combining Scharr Convolution (SC) and Fast Fourier Convolution (FFC) in addition to vertical and horizontal Attention gates (AG) into U- Net. SFA-UNet utilizes double convolution layers with the addition of SC and FFC in its encoder and decoder layers. SC helps to learn the foreground-to-background contrast information whereas FFC provide multi-scale contextual information while mitigating the small objects vanishing problem. Additionally, the introduction of vertical AGs in encoder layers enhances the model's focus on the targeted object by ignoring irrelevant regions. We evaluated the proposed approach on publicly available, SIRST and IRSTD datasets, and achieved superior performance by an average 0.75±0.25% of all combined metrics in multiple runs as compared to the existing state-of-the-art methods. The code can be accessed at https://github.com/imadalishah/SFA_UNeten_US
dc.language.isoenen_US
dc.publisherBSUen_US
dc.subjectматериалы конференцийen_US
dc.subjectattention gatesen_US
dc.subjectISOSen_US
dc.subjectfast Fourier Convolutionen_US
dc.titleSFA-UNet: More Attention to Multi-Scale Contrast and Contextual Information in Infrared Small Object Segmentationen_US
dc.typeArticleen_US
Appears in Collections:Pattern Recognition and Information Processing (PRIP'2023) = Распознавание образов и обработка информации (2023)

Files in This Item:
File Description SizeFormat 
Imad_Ali_Shah_SFA_UNet.pdf550.33 kBAdobe PDFView/Open
Show simple item record Google Scholar

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.