Human-machine knowledge hybrid augmentation method for surface defect detection based few-data learning
Not on the map. Why?
Abstract (arXiv)
Visual-based defect detection is a crucial but challenging task in industrial quality control. Most mainstream methods rely on large amounts of existing or related domain data as auxiliary information. However, in actual industrial production, there are often multi-batch, low-volume manufacturing scenarios with rapidly changing task demands, making it difficult to obtain sufficient and diverse defect data. This paper proposes a parallel solution that uses a human-machine knowledge hybrid augmentation method to help the model extract unknown important features. Specifically, by incorporating experts' knowledge of abnormality to create data with rich features, positions, sizes, and backgrounds, we can quickly accumulate an amount of data from scratch and provide it to the model as prior knowledge for few-data learning. The proposed method was evaluated on the magnetic tile dataset and achieved F1-scores of 60.73%, 70.82%, 77.09%, and 82.81% when using 2, 5, 10, and 15 training images, respectively. Compared to the traditional augmentation method's F1-score of 64.59%, the proposed method achieved an 18.22% increase in the best result, demonstrating its feasibility and effectiveness in few-data industrial defect detection.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 80 references that are in the map. First posted on arXiv 27 Apr 2023.
Builds on
28 of 80 references.
References · 28
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
- 2015SSD: Single Shot MultiBox Detectorcited by 3,130
- 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
- 2020Meta-Learning in Neural Networks: A Surveycited by 950
- 2016Playing for Data: Ground Truth from Computer Gamescited by 818
- 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
- 2017Feature Generating Networks for Zero-Shot Learningcited by 257
- 2021A Survey of Human-in-the-loop for Machine Learningcited by 215
- 2016Learning a Deep Embedding Model for Zero-Shot Learningcited by 153
- 2019Seeing What a GAN Cannot Generatecited by 148
- 2017Generalized Zero-Shot Learning via Synthesized Examplescited by 114
- 2016Synthesized Classifiers for Zero-Shot Learningcited by 113
16 more
- 2017Few-Shot Adversarial Domain Adaptationcited by 111
- 2017A Generative Adversarial Approach for Zero-Shot Learning from Noisy Textscited by 96
- 2018Delta-encoder: an effective sample synthesis method for few-shot object recognitioncited by 89
- 2016Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classificationcited by 85
- 2021Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspectioncited by 77
- 2019Graph Few-shot Learning via Knowledge Transfercited by 63
- 2021A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detectioncited by 60
- 2016One-Shot Generalization in Deep Generative Modelscited by 45
- 2019Few-shot Adaptive Faster R-CNNcited by 42
- 2018Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Datacited by 25
- 2018The Variational Homoencoder: Learning to learn high capacity generative models from few examplescited by 23
- 2017From Zero-shot Learning to Conventional Supervised Classification: Unseen Visual Data Synthesiscited by 21
- 2019Meta-learning Convolutional Neural Architectures for Multi-target Concrete Defect Classification with the COncrete DEfect BRidge IMage Datasetcited by 21
- 2017Zero-Shot Recognition using Dual Visual-Semantic Mapping Pathscited by 20
- 2017Transductive Zero-Shot Learning with a Self-training dictionary approachcited by 7
- 2016Few-Shot Object Recognition from Machine-Labeled Web Imagescited by 6
Built on by
Not cited yet.