# Distance-Based Anomaly Detection for Industrial Surfaces Using Triplet Networks

arXiv: https://arxiv.org/abs/2011.04121 · HTML: https://mlsanity.com/paper/2011.04121/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Nov 2020.

## Built on by (most cited first, 13 of 13)

- [CutPaste: Self-Supervised Learning for Anomaly Detection and Localization](https://mlsanity.com/paper/2104.04015/) (2021)
- [Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey](https://mlsanity.com/paper/2207.10298/) (2022)
- [PWPAE: An Ensemble Framework for Concept Drift Adaptation in IoT Data Streams](https://mlsanity.com/paper/2109.05013/) (2021)
- [Transfer Learning Gaussian Anomaly Detection by Fine-tuning Representations](https://mlsanity.com/paper/2108.04116/) (2021)
- [REB: Reducing Biases in Representation for Industrial Anomaly Detection](https://mlsanity.com/paper/2308.12577/) (2023)
- [Multi-Perspective Content Delivery Networks Security Framework Using Optimized Unsupervised Anomaly Detection](https://mlsanity.com/paper/2107.11514/) (2021)
- [An Attention-based ConvLSTM Autoencoder with Dynamic Thresholding for Unsupervised Anomaly Detection in Multivariate Time Series](https://mlsanity.com/paper/2201.09172/) (2022)
- [On the Intersection of Signal Processing and Machine Learning: A Use Case-Driven Analysis Approach](https://mlsanity.com/paper/2403.17181/) (2024)
- [A Novel Center-based Deep Contrastive Metric Learning Method for the Detection of Polymicrogyria in Pediatric Brain MRI](https://mlsanity.com/paper/2211.12565/) (2022)
- [IoT Network Traffic Analysis with Deep Learning](https://mlsanity.com/paper/2402.04469/) (2024)
- [Applying Deep Learning to Anomaly Detection of Russian Satellite Activity for Indications Prior to Military Activity](https://mlsanity.com/paper/2509.00050/) (2025)
- [High Dimensional Data Decomposition for Anomaly Detection of Textured Images](https://mlsanity.com/paper/2512.20432/) (2025)
- [Beyond Normal References: Discriminative Few-Shot Anomaly Detection](https://mlsanity.com/paper/2605.23231/) (2026)

## Abstract (arXiv)

Surface anomaly detection plays an important quality control role in many manufacturing industries to reduce scrap production. Machine-based visual inspections have been utilized in recent years to conduct this task instead of human experts. In particular, deep learning Convolutional Neural Networks (CNNs) have been at the forefront of these image processing-based solutions due to their predictive accuracy and efficiency. Training a CNN on a classification objective requires a sufficiently large amount of defective data, which is often not available. In this paper, we address that challenge by training the CNN on surface texture patches with a distance-based anomaly detection objective instead. A deep residual-based triplet network model is utilized, and defective training samples are synthesized exclusively from non-defective samples via random erasing techniques to directly learn a similarity metric between the same-class samples and out-of-class samples. Evaluation results demonstrate the approach's strength in detecting different types of anomalies, such as bent, broken, or cracked surfaces, for known surfaces that are part of the training data and unseen novel surfaces.