MicroCrackAttentionNeXt: Advancing Microcrack Detection in Wave Field Analysis Using Deep Neural Networks through Feature Visualization

TL;DR

This paper enhances microcrack detection in wave field analysis by optimizing deep neural network architectures and training methods, addressing class imbalance and utilizing feature visualization to improve accuracy.

Contribution

It introduces optimized neural network architecture and training strategies for microcrack detection, leveraging feature visualization to understand model behavior.

Findings

Achieved 86.85% detection accuracy.

Analyzed activation and loss functions impact.

Utilized feature visualization for model insights.

Abstract

Micro Crack detection using deep neural networks (DNNs) through an automated pipeline using wave fields interacting with the damaged areas is highly sought after. These high-dimensional spatio-temporal crack data are limited, and these datasets have large dimensions in the temporal domain. The dataset presents a substantial class imbalance, with crack pixels constituting an average of only 5% of the total pixels per sample. This extreme class imbalance poses a challenge for deep learning models with the different micro-scale cracks, as the network can be biased toward predicting the majority class, generally leading to poor detection accuracy. This study builds upon the previous benchmark SpAsE-Net, an asymmetric encoder-decoder network for micro-crack detection. The impact of various activation and loss functions were examined through feature space visualization using the manifold discovery and analysis (MDA) algorithm. The optimized architecture and training methodology achieved an accuracy of 86.85%.