# TrueDeep: A systematic approach of crack detection with less data

arXiv: https://arxiv.org/abs/2305.19088 · HTML: https://mlsanity.com/paper/2305.19088/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 45 references that are in the map.
- First posted on arXiv 30 May 2023.

## Builds on (most cited first, 7 of 7)

- [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)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [Carbon Emissions and Large Neural Network Training](https://mlsanity.com/paper/2104.10350/) (2021)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [CoreDeep: Improving Crack Detection Algorithms Using Width Stochasticity](https://mlsanity.com/paper/2209.04648/) (2022)

## Built on by (most cited first, 1 of 1)

- [Revealing the Underlying Patterns: Investigating Dataset Similarity, Performance, and Generalization](https://mlsanity.com/paper/2308.03580/) (2023)

## Abstract (arXiv)

Supervised and semi-supervised semantic segmentation algorithms require significant amount of annotated data to achieve a good performance. In many situations, the data is either not available or the annotation is expensive. The objective of this work is to show that by incorporating domain knowledge along with deep learning architectures, we can achieve similar performance with less data. We have used publicly available crack segmentation datasets and shown that selecting the input images using knowledge can significantly boost the performance of deep-learning based architectures. Our proposed approaches have many fold advantages such as low annotation and training cost, and less energy consumption. We have measured the performance of our algorithm quantitatively in terms of mean intersection over union (mIoU) and F score. Our algorithms, developed with 23% of the overall data; have a similar performance on the test data and significantly better performance on multiple blind datasets.