FlexiCrackNet: A Flexible Pipeline for Enhanced Crack Segmentation with General Features Transfered from SAM

2025-01-31

AI Summary

To address the low segmentation accuracy and poor generalization of existing methods on low-performance devices—particularly under challenging conditions such as blurry images, complex backgrounds, and faint cracks—this paper proposes a lightweight and robust end-to-end crack segmentation framework. Methodologically, it decouples universal feature extraction (via an enhanced EdgeSAM encoder that removes fixed-resolution constraints) from task-specific decoding, and introduces the Information-Gated Attention Mechanism (IGAM), a novel module enabling adaptive multi-scale feature fusion. Contributions include: (1) the first crack segmentation framework supporting zero-shot cross-domain generalization at arbitrary input resolutions; (2) state-of-the-art performance across multiple benchmarks; (3) efficient inference with low GPU memory footprint; and (4) superior robustness against image blur, noise, and visual ambiguity.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Automatic crack segmentation is a cornerstone technology for intelligent visual perception modules in road safety maintenance and structural integrity systems. Existing deep learning models and ``pre-training + fine-tuning'' paradigms often face challenges of limited adaptability in resource-constrained environments and inadequate scalability across diverse data domains. To overcome these limitations, we propose FlexiCrackNet, a novel pipeline that seamlessly integrates traditional deep learning paradigms with the strengths of large-scale pre-trained models. At its core, FlexiCrackNet employs an encoder-decoder architecture to extract task-specific features. The lightweight EdgeSAM's CNN-based encoder is exclusively used as a generic feature extractor, decoupled from the fixed input size requirements of EdgeSAM. To harmonize general and domain-specific features, we introduce the information-Interaction gated attention mechanism (IGAM), which adaptively fuses multi-level features to enhance segmentation performance while mitigating irrelevant noise. This design enables the efficient transfer of general knowledge to crack segmentation tasks while ensuring adaptability to diverse input resolutions and resource-constrained environments. Experiments show that FlexiCrackNet outperforms state-of-the-art methods, excels in zero-shot generalization, computational efficiency, and segmentation robustness under challenging scenarios such as blurry inputs, complex backgrounds, and visually ambiguous artifacts. These advancements underscore the potential of FlexiCrackNet for real-world applications in automated crack detection and comprehensive structural health monitoring systems.

Problem

• Crack Detection
• Low Performance Devices
• Complex Conditions

Innovation

• FlexiCrackNet
• Knowledge Integration
• Smart Feature Selection