StructureNet: Deep Context Attention Learning for Structural Component Recognition

Kaothalkar, A; Mandal, B; Puhan, NB

Abstract

Structural component recognition using images is a very challenging task due to the appearance of large components and their long continuation, existing jointly with very small components, the latter are often outcasted/missed by the existing methodologies. In this work, various categories of the bridge components are exploited at the contextual level information encoding across spatial as well as channel dimensions. Tensor decomposition is used to design a context attention framework that acquires crucial information across various dimensions by fusing the class contexts and 3-D attention map. Experimental results on benchmarking bridge component classification dataset show that our proposed architecture attains superior results as compared to the current state-of-the-art methodologies.

Citation

Kaothalkar, A., Mandal, B., & Puhan, N. (2022). StructureNet: Deep Context Attention Learning for Structural Component Recognition. . https://doi.org/10.5220/0010872800003124

• Conference Name: 17th International Conference on Computer Vision Theory and Applications
• Conference Location: Virtual
• Start Date: Feb 6, 2022
• End Date: Feb 8, 2022
• Acceptance Date: Feb 6, 2022
• Publication Date: Feb 8, 2022
• Publicly Available Date: May 30, 2023
• Series Title: 17th International Conference on Computer Vision Theory and Applications
• ISBN: 978-989-758-555-5
• DOI: https://doi.org/10.5220/0010872800003124
• Keywords: Class Contexts, Context Attention, Semantic Segmentation, Structural Component Recognition.
• Publisher URL: https://www.scitepress.org/Link.aspx?doi=10.5220/0010872800003124