MN-Pair Contrastive Damage Representation and Clustering for Prognostic Explanation

TL;DR

This paper introduces MN-pair contrastive learning for damage representation in infrastructure inspection, enabling detailed clustering of unseen damages and providing visual explanations, thus improving damage classification beyond predefined damage grades.

Contribution

The paper presents a novel MN-pair contrastive learning approach that enhances damage embedding and clustering, surpassing traditional N-pair methods and incorporating visualization for interpretability.

Findings

Faster learning compared to N-pair algorithm.

Effective clustering of unseen damage types.

Visual explanations via Grad-CAM improve interpretability.

Abstract

For infrastructure inspections, damage representation does not constantly match the predefined classes of damage grade, resulting in detailed clusters of unseen damages or more complex clusters from overlapped space between two grades. The damage representation has fundamentally complex features; consequently, not all the damage classes can be perfectly predefined. The proposed MN-pair contrastive learning method helps to explore an embedding damage representation beyond the predefined classes by including more detailed clusters. It maximizes both the similarity of M-1 positive images close to an anchor and dissimilarity of N-1 negative images using both weighting loss functions. It learns faster than the N-pair algorithm using one positive image. We proposed a pipeline to obtain the damage representation and used a density-based clustering on a 2-D reduction space to automate finer cluster discrimination. We also visualized the explanation of the damage feature using Grad-CAM for MN-pair damage metric learning. We demonstrated our method in three experimental studies: steel product defect, concrete crack, and the effectiveness of our method and discuss future works.