A Masked Autoencoder Approach to Unsupervised Steel Surface Defect Recognition

• URL: http://arxiv.org/abs/2607.13178v1
• Date: Tue, 14 Jul 2026 18:26:36 GMT
• Title: A Masked Autoencoder Approach to Unsupervised Steel Surface Defect Recognition
• Abstract summary: A Transformer based Masked Autoencoder is used here to learn representations of steel surface defects for unsupervised grouping.<n>The decoder reaches a structural similarity score of 0.92 and a mean squared error of 0.47.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automated visual inspection of steel surface defects is a recurring quality control task in which labeled defect data is scarce and costly to obtain, while unlabeled surface images are abundant, which motivates self supervised methods that learn useful representations without class labels. A Transformer based Masked Autoencoder is used here to learn representations of steel surface defects for unsupervised grouping. During pretraining, 75% of the input image patches are randomly masked, and a lightweight decoder reconstructs the masked regions from the visible 25%. The encoder is trained jointly with an auxiliary defect localization objective, used only as a training signal and not evaluated as a detector. The decoder reaches a structural similarity score of 0.92 and a mean squared error of 0.47. Features from the pretrained encoder are then clustered using UMAP for dimensionality reduction and Agglomerative clustering, reaching a Hungarian matched accuracy of 91.3% against the six known defect categories.

Related papers

• An End-to-End Automated Pipeline for Controllable Crack Data Synthesis [16.848359184857912]
  Vision-based crack inspection depends on segmentation networks whose reliability depends on the quantity, diversity and label quality of their training data.<n>This paper presents an end-to-end pipeline that produces labelled crack data without manual annotation and assesses the reliability of these data and of the detectors trained on them.
  arXiv  Detail & Related papers  (2026-09-11T04:40:01Z)
• Addressing Data Scarcity in 3D Trauma Detection through Self-Supervised and Semi-Supervised Learning with Vertex Relative Position Encoding [3.9641557356685166]
  This paper presents a label-efficient approach combining self-supervised pre-training with semi-supervised detection for 3D medical image analysis.<n>We employ patch-based Masked Image Modeling (MIM) to pre-train a 3D U-Net encoder on 1,206 CT volumes without annotations, learning robust anatomical representations.<n>For detection, semi-supervised learning with 2,000 unlabeled volumes and consistency regularization achieves 56.57% validation mAP@0.50 and 45.30% test mAP@0.50 with only 144 labeled training samples.<n>For classification, expanding to 2,244 labeled samples yields 94.07% test accuracy across seven injury
  arXiv  Detail & Related papers  (2026-03-12T23:17:17Z)
• Universal Transformation of One-Class Classifiers for Unsupervised Anomaly Detection [51.73001988341294]
  Anomaly detection is typically formulated as a one-class classification problem.<n>We present a dataset folding method that transforms an arbitrary one-class classifier-based anomaly detector into a fully unsupervised method.
  arXiv  Detail & Related papers  (2026-02-13T16:54:12Z)
• Noise & pattern: identity-anchored Tikhonov regularization for robust structural anomaly detection [58.535473924035365]
  Anomaly detection plays a pivotal role in automated industrial inspection, aiming to identify subtle or rare defects in otherwise uniform visual patterns.<n>We tackle structural anomaly detection using a self-supervised autoencoder that learns to repair corrupted inputs.<n>We introduce a corruption model that injects artificial disruptions into training images to mimic structural defects.
  arXiv  Detail & Related papers  (2025-11-10T15:48:50Z)
• In-Situ Melt Pool Characterization via Thermal Imaging for Defect Detection in Directed Energy Deposition Using Vision Transformers [10.078323907266144]
  Internal defects such as porosity and cracks can compromise mechanical properties and overall performance.<n>This study focuses on in-situ monitoring and characterization of pools associated with porosity, aiming to improve defect detection and quality control in DED-printed parts.
  arXiv  Detail & Related papers  (2024-11-18T20:03:49Z)
• Camouflage is all you need: Evaluating and Enhancing Language Model Robustness Against Camouflage Adversarial Attacks [53.87300498478744]
  Adversarial attacks represent a substantial challenge in Natural Language Processing (NLP) This study undertakes a systematic exploration of this challenge in two distinct phases: vulnerability evaluation and resilience enhancement. Results suggest a trade-off between performance and robustness, with some models maintaining similar performance while gaining robustness.
  arXiv  Detail & Related papers  (2024-02-15T10:58:22Z)
• Anomaly Detection in Automated Fibre Placement: Learning with Data Limitations [3.103778949672542]
  We present a comprehensive framework for defect detection and localization in Automated Fibre Placement. Our approach combines unsupervised deep learning and classical computer vision algorithms. It efficiently detects various surface issues while requiring fewer images of composite parts for training.
  arXiv  Detail & Related papers  (2023-07-15T22:13:36Z)
• Cut and Learn for Unsupervised Object Detection and Instance Segmentation [65.43627672225624]
  Cut-and-LEaRn (CutLER) is a simple approach for training unsupervised object detection and segmentation models. CutLER is a zero-shot unsupervised detector and improves detection performance AP50 by over 2.7 times on 11 benchmarks.
  arXiv  Detail & Related papers  (2023-01-26T18:57:13Z)
• Self-Supervised Training with Autoencoders for Visual Anomaly Detection [61.62861063776813]
  We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. We adapt a self-supervised learning regime that exploits discriminative information during training but focuses on the submanifold of normal examples. We achieve a new state-of-the-art result on the MVTec AD dataset -- a challenging benchmark for visual anomaly detection in the manufacturing domain.
  arXiv  Detail & Related papers  (2022-06-23T14:16:30Z)
• Reference-based Defect Detection Network [57.89399576743665]
  The first issue is the texture shift which means a trained defect detector model will be easily affected by unseen texture. The second issue is partial visual confusion which indicates that a partial defect box is visually similar with a complete box. We propose a Reference-based Defect Detection Network (RDDN) to tackle these two problems.
  arXiv  Detail & Related papers  (2021-08-10T05:44:23Z)
• CutPaste: Self-Supervised Learning for Anomaly Detection and Localization [59.719925639875036]
  We propose a framework for building anomaly detectors using normal training data only. We first learn self-supervised deep representations and then build a generative one-class classifier on learned representations. Our empirical study on MVTec anomaly detection dataset demonstrates the proposed algorithm is general to be able to detect various types of real-world defects.
  arXiv  Detail & Related papers  (2021-04-08T19:04:55Z)
• Semi-supervised Anomaly Detection using AutoEncoders [0.0]
  Anomaly detection refers to the task of finding unusual instances that stand out from the normal data. In this paper, we present a convolutional auto-encoder architecture for anomaly detection that is trained only on the defect-free (normal) instances. The approach was tested on two data-sets and achieved an impressive average F1 score of 0.885.
  arXiv  Detail & Related papers  (2020-01-06T23:06:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.