FORTRESS: Function-composition Optimized Real-Time Resilient Structural Segmentation via Kolmogorov-Arnold Enhanced Spatial Attention Networks

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Thrainer, Christina, Ferdaus, Md Meftahul, Abdelguerfi, Mahdi, Guetl, Christian, Sloan, Steven, Niles, Kendall N., Pathak, Ken
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908453914542080
author Thrainer, Christina
Ferdaus, Md Meftahul
Abdelguerfi, Mahdi
Guetl, Christian
Sloan, Steven
Niles, Kendall N.
Pathak, Ken
author_facet Thrainer, Christina
Ferdaus, Md Meftahul
Abdelguerfi, Mahdi
Guetl, Christian
Sloan, Steven
Niles, Kendall N.
Pathak, Ken
contents Automated structural defect segmentation in civil infrastructure faces a critical challenge: achieving high accuracy while maintaining computational efficiency for real-time deployment. This paper presents FORTRESS (Function-composition Optimized Real-Time Resilient Structural Segmentation), a new architecture that balances accuracy and speed by using a special method that combines depthwise separable convolutions with adaptive Kolmogorov-Arnold Network integration. FORTRESS incorporates three key innovations: a systematic depthwise separable convolution framework achieving a 3.6x parameter reduction per layer, adaptive TiKAN integration that selectively applies function composition transformations only when computationally beneficial, and multi-scale attention fusion combining spatial, channel, and KAN-enhanced features across decoder levels. The architecture achieves remarkable efficiency gains with 91% parameter reduction (31M to 2.9M), 91% computational complexity reduction (13.7 to 1.17 GFLOPs), and 3x inference speed improvement while delivering superior segmentation performance. Evaluation on benchmark infrastructure datasets demonstrates state-of-the-art results with an F1- score of 0.771 and a mean IoU of 0.677, significantly outperforming existing methods including U-Net, SA-UNet, and U- KAN. The dual optimization strategy proves essential for optimal performance, establishing FORTRESS as a robust solution for practical structural defect segmentation in resource-constrained environments where both accuracy and computational efficiency are paramount. Comprehensive architectural specifications are provided in the Supplemental Material. Source code is available at URL: https://github.com/faeyelab/fortress-paper-code.
format Preprint
id arxiv_https___arxiv_org_abs_2507_12675
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FORTRESS: Function-composition Optimized Real-Time Resilient Structural Segmentation via Kolmogorov-Arnold Enhanced Spatial Attention Networks
Thrainer, Christina
Ferdaus, Md Meftahul
Abdelguerfi, Mahdi
Guetl, Christian
Sloan, Steven
Niles, Kendall N.
Pathak, Ken
Computer Vision and Pattern Recognition
Artificial Intelligence
Image and Video Processing
Automated structural defect segmentation in civil infrastructure faces a critical challenge: achieving high accuracy while maintaining computational efficiency for real-time deployment. This paper presents FORTRESS (Function-composition Optimized Real-Time Resilient Structural Segmentation), a new architecture that balances accuracy and speed by using a special method that combines depthwise separable convolutions with adaptive Kolmogorov-Arnold Network integration. FORTRESS incorporates three key innovations: a systematic depthwise separable convolution framework achieving a 3.6x parameter reduction per layer, adaptive TiKAN integration that selectively applies function composition transformations only when computationally beneficial, and multi-scale attention fusion combining spatial, channel, and KAN-enhanced features across decoder levels. The architecture achieves remarkable efficiency gains with 91% parameter reduction (31M to 2.9M), 91% computational complexity reduction (13.7 to 1.17 GFLOPs), and 3x inference speed improvement while delivering superior segmentation performance. Evaluation on benchmark infrastructure datasets demonstrates state-of-the-art results with an F1- score of 0.771 and a mean IoU of 0.677, significantly outperforming existing methods including U-Net, SA-UNet, and U- KAN. The dual optimization strategy proves essential for optimal performance, establishing FORTRESS as a robust solution for practical structural defect segmentation in resource-constrained environments where both accuracy and computational efficiency are paramount. Comprehensive architectural specifications are provided in the Supplemental Material. Source code is available at URL: https://github.com/faeyelab/fortress-paper-code.
title FORTRESS: Function-composition Optimized Real-Time Resilient Structural Segmentation via Kolmogorov-Arnold Enhanced Spatial Attention Networks
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Image and Video Processing
url https://arxiv.org/abs/2507.12675