Cracks in the Foundation: A Civil Infrastructure Dataset to Challenge Vision Foundation Models

TL;DR

This paper introduces the Cracks in the Foundation (CiF) dataset, the largest civil infrastructure segmentation dataset, revealing significant gaps in current AI models' ability to understand real-world structural images.

Contribution

The creation of the CiF dataset provides a new benchmark for civil infrastructure defect segmentation, exposing limitations of current foundation and vision models in practical applications.

Findings

Current foundation models struggle with real-world infrastructure images.

Specialized models plateau at approximately 25% mAP on the new dataset.

Even state-of-the-art models face significant challenges in dense image understanding of civil structures.

Abstract

Automated structural health monitoring is essential to prevent catastrophic infrastructure failures. Precise, pixel-level defect segmentation is needed to accurately assess structural integrity, but progress in defect segmentation for civil infrastructures has been held back by an extreme scarcity of data, which requires costly expert annotation. The need for data is accentuated by algorithmic hurdles intrinsic to the problem, including center-bias and the need to rely more on shape when inspecting nearly textureless building materials. To remove the bottleneck, we introduce Cracks in the Foundation (CiF), the largest and most detailed civil infrastructure (instance) segmentation dataset to date, comprising $\approx$150,000 high-resolution images meticulously curated over five years in collaboration with civil engineering experts. With the help of this unprecedented data source, we expose a blind spot of current visual AI: despite the advent of promptable Foundation Models (FMs) and Vision Language Models (VLMs), and despite the impressive abilities of today's specialised segmentation models, it turns out that dense image understanding in the built environment is nowhere near solved. Our evaluations indicate that even the most recent zero-shot FMs face significant challenges when deployed on real-world infrastructure and even the performance of specialised models with domain-specific supervision plateaus at $\approx$25% mAP. CiF establishes inspection of civil infrastructure, an elementary and seemingly easy perceptual task, as an open challenge that reveals fundamental weaknesses of present-day models trained predominantly on internet images, literally and figuratively highlighting cracks in the current foundation model paradigm.