# Weakly-Supervised Surface Crack Segmentation by Generating Pseudo-Labels using Localization with a Classifier and Thresholding

arXiv: https://arxiv.org/abs/2109.00456 · HTML: https://mlsanity.com/paper/2109.00456/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 35 references that are in the map.
- First posted on arXiv 1 Sep 2021.

## Builds on (most cited first, 11 of 11)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/1803.10464/) (2018)
- [Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection](https://mlsanity.com/paper/1901.06340/) (2019)
- [Road Crack Detection Using Deep Convolutional Neural Network and Adaptive Thresholding](https://mlsanity.com/paper/1904.08582/) (2019)
- [Automatic Pavement Crack Detection Based on Structured Prediction with the Convolutional Neural Network](https://mlsanity.com/paper/1802.02208/) (2018)
- [Optimized Deep Encoder-Decoder Methods for Crack Segmentation](https://mlsanity.com/paper/2008.06266/) (2020)
- [Crack Detection as a Weakly-Supervised Problem: Towards Achieving Less Annotation-Intensive Crack Detectors](https://mlsanity.com/paper/2011.02208/) (2020)

## Built on by (most cited first, 6 of 6)

- [Weakly-Supervised Crack Detection](https://mlsanity.com/paper/2206.06743/) (2022)
- [CrackCLF: Automatic Pavement Crack Detection based on Closed-Loop Feedback](https://mlsanity.com/paper/2311.11815/) (2023)
- [Vehicular Road Crack Detection with Deep Learning: A New Online Benchmark for Comprehensive Evaluation of Existing Algorithms](https://mlsanity.com/paper/2503.18082/) (2025)
- [Deep Learning for Crack Detection: A Review of Learning Paradigms, Generalizability, and Datasets](https://mlsanity.com/paper/2508.10256/) (2025)
- [CrackUDA: Incremental Unsupervised Domain Adaptation for Improved Crack Segmentation in Civil Structures](https://mlsanity.com/paper/2412.15637/) (2024)
- [WP-CrackNet: A Collaborative Adversarial Learning Framework for End-to-End Weakly-Supervised Road Crack Detection](https://mlsanity.com/paper/2510.17566/) (2025)

## Abstract (arXiv)

Surface cracks are a common sight on public infrastructure nowadays. Recent work has been addressing this problem by supporting structural maintenance measures using machine learning methods. Those methods are used to segment surface cracks from their background, making them easier to localize. However, a common issue is that to create a well-functioning algorithm, the training data needs to have detailed annotations of pixels that belong to cracks. Our work proposes a weakly supervised approach that leverages a CNN classifier in a novel way to create surface crack pseudo labels. First, we use the classifier to create a rough crack localization map by using its class activation maps and a patch based classification approach and fuse this with a thresholding based approach to segment the mostly darker crack pixels. The classifier assists in suppressing noise from the background regions, which commonly are incorrectly highlighted as cracks by standard thresholding methods. Then, the pseudo labels can be used in an end-to-end approach when training a standard CNN for surface crack segmentation. Our method is shown to yield sufficiently accurate pseudo labels. Those labels, incorporated into segmentation CNN training using multiple recent crack segmentation architectures, achieve comparable performance to fully supervised methods on four popular crack segmentation datasets.