Affiliation:
1. Key Laboratory of Big Data Artificial Intelligence in Transportation (Beijing Jiaotong University), Ministry of Education, Beijing 100044, China
2. School of Computer Science and Technology, Jiangsu Normal University, Xuzhou 221116, China
Abstract
Automatic crack segmentation plays an essential role in maintaining the structural health of buildings and infrastructure. Despite the success in fully supervised crack segmentation, the costly pixel-level annotation restricts its application, leading to increased exploration in weakly supervised crack segmentation (WSCS). However, WSCS methods inevitably bring in noisy pseudo-labels, which results in large fluctuations. To address this problem, we propose a novel confidence-aware co-training (CAC) framework for WSCS. This framework aims to iteratively refine pseudo-labels, facilitating the learning of a more robust segmentation model. Specifically, a co-training mechanism is designed and constructs two collaborative networks to learn uncertain crack pixels, from easy to hard. Moreover, the dynamic division strategy is designed to divide the pseudo-labels based on the crack confidence score. Among them, the high-confidence pseudo-labels are utilized to optimize the initialization parameters for the collaborative network, while low-confidence pseudo-labels enrich the diversity of crack samples. Extensive experiments conducted on the Crack500, DeepCrack, and CFD datasets demonstrate that the proposed CAC significantly outperforms other WSCS methods.
Funder
Fundamental Research Funds for the Central Universities
Beijing Natural Science Foundatio
Shanghai Industrial Development Project
Reference53 articles.
1. Munawar, H.S., Hammad, A.W.A., Haddad, A., Soares, C.A.P., and Waller, S.T. (2021). Image-Based Crack Detection Methods: A Review. Infrastructures, 6.
2. Yu, X., Kuan, T.W., Tseng, S.P., Chen, Y., Chen, S., Wang, J.F., Gu, Y., and Chen, T. (2023). EnRDeA U-net deep learning of semantic segmentation on intricate noise roads. Entropy, 25.
3. A deeper generative adversarial network for grooved cement concrete pavement crack detection;Zhong;Eng. Appl. Artif. Intell.,2023
4. Computer vision framework for crack detection of civil infrastructure—A review;Ai;Eng. Appl. Artif. Intell.,2023
5. Building crack identification and total quality management method based on deep learning;Wu;Pattern Recognit. Lett.,2021