# SCNet: A Generalized Attention-based Model for Crack Fault Segmentation

arXiv: https://arxiv.org/abs/2112.01426 · HTML: https://mlsanity.com/paper/2112.01426/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 66 references that are in the map.
- First posted on arXiv 2 Dec 2021.

## Builds on (most cited first, 22 of 22)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [CCNet: Criss-Cross Attention for Semantic Segmentation](https://mlsanity.com/paper/1811.11721/) (2018)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [Attention to Scale: Scale-aware Semantic Image Segmentation](https://mlsanity.com/paper/1511.03339/) (2015)
- [Pyramid Attention Network for Semantic Segmentation](https://mlsanity.com/paper/1805.10180/) (2018)
- [Mixed supervision for surface-defect detection: from weakly to fully supervised learning](https://mlsanity.com/paper/2104.06064/) (2021)
- [IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis](https://mlsanity.com/paper/1807.06358/) (2018)
- [Material Recognition in the Wild with the Materials in Context Database](https://mlsanity.com/paper/1412.0623/) (2014)
- [Segmentation-Aware Convolutional Networks Using Local Attention Masks](https://mlsanity.com/paper/1708.04607/) (2017)
- [Meta-learning Convolutional Neural Architectures for Multi-target Concrete Defect Classification with the COncrete DEfect BRidge IMage Dataset](https://mlsanity.com/paper/1904.08486/) (2019)
- [Optimized Deep Encoder-Decoder Methods for Crack Segmentation](https://mlsanity.com/paper/2008.06266/) (2020)
- [Deep Multi-task Learning for Railway Track Inspection](https://mlsanity.com/paper/1509.05267/) (2015)
- [Crack Detection Using Enhanced Hierarchical Convolutional Neural Networks](https://mlsanity.com/paper/1912.12139/) (2019)

## Abstract (arXiv)

Anomaly detection and localization is an important vision problem, having multiple applications. Effective and generic semantic segmentation of anomalous regions on various different surfaces, where most anomalous regions inherently do not have any obvious pattern, is still under active research. Periodic health monitoring and fault (anomaly) detection in vast infrastructures, which is an important safety-related task, is one such application area of vision-based anomaly segmentation. However, the task is quite challenging due to large variations in surface faults, texture-less construction material/background, lighting conditions etc. Cracks are critical and frequent surface faults that manifest as extreme zigzag-shaped thin, elongated regions. They are among the hardest faults to detect, even with deep learning. In this work, we address an open aspect of automatic crack segmentation problem, that of generalizing and improving the performance of segmentation across a variety of scenarios, by modeling the problem differently. We carefully study and abstract the sub-problems involved and solve them in a broader context, making our solution generic. On a variety of datasets related to surveillance of different infrastructures, under varying conditions, our model consistently outperforms the state-of-the-art algorithms by a significant margin, without any bells-and-whistles. This performance advantage easily carried over in two deployments of our model, tested against industry-provided datasets. Even further, we could establish our model's performance for two manufacturing quality inspection scenarios as well, where the defect types are not just crack equivalents, but much more and different. Hence we hope that our model is indeed a truly generic defect segmentation model.