WP-CrackNet: A Collaborative Adversarial Learning Framework for End-to-End Weakly-Supervised Road Crack Detection

TL;DR

WP-CrackNet is a novel weakly-supervised framework for pixel-wise road crack detection that leverages adversarial learning and attention modules to achieve high accuracy with only image-level labels.

Contribution

It introduces a collaborative adversarial learning framework with novel modules for improved weakly-supervised crack detection, reducing the need for pixel-level annotations.

Findings

Achieves comparable results to fully supervised methods.

Outperforms existing weakly-supervised approaches.

Demonstrates effectiveness on three new datasets.

Abstract

Road crack detection is essential for intelligent infrastructure maintenance in smart cities. To reduce reliance on costly pixel-level annotations, we propose WP-CrackNet, an end-to-end weakly-supervised method that trains with only image-level labels for pixel-wise crack detection. WP-CrackNet integrates three components: a classifier generating class activation maps (CAMs), a reconstructor measuring feature inferability, and a detector producing pixel-wise road crack detection results. During training, the classifier and reconstructor alternate in adversarial learning to encourage crack CAMs to cover complete crack regions, while the detector learns from pseudo labels derived from post-processed crack CAMs. This mutual feedback among the three components improves learning stability and detection accuracy. To further boost detection performance, we design a path-aware attention module (PAAM) that fuses high-level semantics from the classifier with low-level structural cues from the reconstructor by modeling spatial and channel-wise dependencies. Additionally, a center-enhanced CAM consistency module (CECCM) is proposed to refine crack CAMs using center Gaussian weighting and consistency constraints, enabling better pseudo-label generation. We create three image-level datasets and extensive experiments show that WP-CrackNet achieves comparable results to supervised methods and outperforms existing weakly-supervised methods, significantly advancing scalable road inspection. The source code package and datasets are available at https://mias.group/WP-CrackNet/.