MA-UNet model for crack segmentation in concrete structures utilizing Mamba skip connections in multiple scenarios
Concrete structures are prone to cracking during service, which, if left undetected, can lead to severe structural failure. Current deep learning paradigms face significant limitations: Convolutional Neural Networks (CNNs) are constrained by local receptive fields, hindering the capture of global co...
שמור ב:
| Principais autores: | , , , |
|---|---|
| פורמט: | Artigo |
| שפה: | Inglês |
| יצא לאור: |
Taylor & Francis Group
2026-04-01
|
| סדרה: | Journal of Asian Architecture and Building Engineering |
| נושאים: | |
| גישה מקוונת: | http://dx.doi.org/10.1080/13467581.2026.2651001 |
| תגים: |
אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!
|