English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Large-scale foundation models have become the mainstream deep learningmethod, while in civil engineering, the scale of AI models is strictly limited.In this work, a vision foundation model is introduced for crack segmentation.Two parameter-efficient fine-tuning methods, adapter and low-rank adaptation,are adopted to fine-tune the foundation model in semantic segmentation: theSegment Anything Model (SAM). The fine-tuned CrackSAM model is much larger thanall the existing crack segmentation models but shows excellent performance. Totest the zero-shot performance of the proposed method, two unique datasetsrelated to road and exterior wall cracks are collected, annotated andopen-sourced, for a total of 810 images. Comparative experiments are conductedwith twelve mature semantic segmentation models. On datasets with artificialnoise and previously unseen datasets, the performance of CrackSAM far exceedsthat of all state-of-the-art models. CrackSAM exhibits remarkable superiority,particularly under challenging conditions such as dim lighting, shadows, roadmarkings, construction joints, and other interference factors. Thesecross-scenario results demonstrate the outstanding zero-shot capability offoundation models and provide new ideas for developing vision models in civilengineering.

Fine-tuning vision foundation model for crack segmentation in civil infrastructures