# Learning Trustworthy Model from Noisy Labels based on Rough Set for Surface Defect Detection

arXiv: https://arxiv.org/abs/2301.10441 · HTML: https://mlsanity.com/paper/2301.10441/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 47 references that are in the map.
- First posted on arXiv 25 Jan 2023.

## Builds on (most cited first, 24 of 24)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [Learning from Noisy Labels with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2007.08199/) (2020)
- [DropBlock: A regularization method for convolutional networks](https://mlsanity.com/paper/1810.12890/) (2018)
- [Tversky loss function for image segmentation using 3D fully convolutional deep networks](https://mlsanity.com/paper/1706.05721/) (2017)
- [Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding](https://mlsanity.com/paper/1511.02680/) (2015)
- [Does label smoothing mitigate label noise?](https://mlsanity.com/paper/2003.02819/) (2020)
- [Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference](https://mlsanity.com/paper/1506.02158/) (2015)
- [Deep Bilevel Learning](https://mlsanity.com/paper/1809.01465/) (2018)
- [Deep Learning from Noisy Image Labels with Quality Embedding](https://mlsanity.com/paper/1711.00583/) (2017)
- [MOCCA: Multi-Layer One-Class ClassificAtion for Anomaly Detection](https://mlsanity.com/paper/2012.12111/) (2020)
- [Pick-and-Learn: Automatic Quality Evaluation for Noisy-Labeled Image Segmentation](https://mlsanity.com/paper/1907.11835/) (2019)
- [Automated Muscle Segmentation from Clinical CT using Bayesian U-Net for Personalized Musculoskeletal Modeling](https://mlsanity.com/paper/1907.08915/) (2019)
- [Learning from Pixel-Level Label Noise: A New Perspective for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2103.14242/) (2021)
- [Can Image-Level Labels Replace Pixel-Level Labels for Image Parsing](https://mlsanity.com/paper/1403.1626/) (2014)
- [Learning from Ambiguous Labels for Lung Nodule Malignancy Prediction](https://mlsanity.com/paper/2104.11436/) (2021)
- [RAR-U-Net: a Residual Encoder to Attention Decoder by Residual Connections Framework for Spine Segmentation under Noisy Labels](https://mlsanity.com/paper/2009.12873/) (2020)
- [Learning to segment fetal brain tissue from noisy annotations](https://mlsanity.com/paper/2203.14962/) (2022)

## Abstract (arXiv)

In the surface defect detection, there are some suspicious regions that cannot be uniquely classified as abnormal or normal. The annotating of suspicious regions is easily affected by factors such as workers' emotional fluctuations and judgment standard, resulting in noisy labels, which in turn leads to missing and false detections, and ultimately leads to inconsistent judgments of product quality. Unlike the usual noisy labels, the ones used for surface defect detection appear to be inconsistent rather than mislabeled. The noise occurs in almost every label and is difficult to correct or evaluate. In this paper, we proposed a framework that learns trustworthy models from noisy labels for surface defect defection. At first, to avoid the negative impact of noisy labels on the model, we represent the suspicious regions with consistent and precise elements at the pixel-level and redesign the loss function. Secondly, without changing network structure and adding any extra labels, pluggable spatially correlated Bayesian module is proposed. Finally, the defect discrimination confidence is proposed to measure the uncertainty, with which anomalies can be identified as defects. Our results indicate not only the effectiveness of the proposed method in learning from noisy labels, but also robustness and real-time performance.