Dataset

1. Steel surface defects: NEU-CLS: [Link]

2. Solar panel: elpv-dataset [Link]

3. Metal surface: KolektorSDD [Link]

4. PCB board inspection: DeepPCB [Link]

5. AITEX data set (fabric defect) [Link] - Extraction code: b9uy

6. Tianchi fabric defect data (competition) [Link] - Extraction code: gat2

7. Industrial optical inspection under weakly supervised learning (DAGM 2007) [Link]

8. Inspection data of surface cracks in infrastructure [Link] - Extraction code: jajn

9. Magnetic tile dataset [Link]

10. Texture dataset [Link]

11. RSDDs dataset [Link]

12. Wood defect dataset [Link]

13. Bridge cracks [Link]

14. Crack on road surface [Link]

Anomaly Detection

1. InsPLAD-fault.

2. MVTec AD.

3. Semiconductor Wafer.

Style and Content Difference (related to layer and defect)

• [IBN-Net] Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net_2020 [Paper] [Code]

Survey

• Fabric Defect Detection in Textile Manufacturing: A Survey of the State of the Art [Paper] [Personal Summary]

• Progressive Semantic Segmentation [Paper] 

• Road Object Detection: A Comparative Study of Deep Learning-Based Algorithms [Paper]

Related Works

• Towards Light-weight and Real-time Line Segment Detection [Paper] [Code] 

• HCCA-UNet: Hyper Column and Context Attention Based UNet for Multi-Organ Nuclei Segmentation [Paper]

Fabric Defect Detection in Textile: [Personal Summary]

• Self-attention Deep Saliency Network for Fabric Defect Detection_2020

• MLMA-Net: multi-level multi-attentional learning for multi-label object detection in textile defect images_2021

• Fabric Defect Segmentation Method Based on Deep Learning_2020

• A Robust Fabric Defect Detection Method Based on Improved RefineDet_2020

• Automatic Fabric Defect Detection with a Multi-Scale Convolutional Denoising Autoencoder Network Model_2018

• Defective texture classification using optimized neural network structure_2020

• Research on Fabric Defect Detection Based on Deep Fusion DenseNet-SSD Network_2020

• Fabric Defect Detection System Using Stacked Convolutional Denoising Auto-Encoders Trained with Synthetic Defect Data_2020

• Yarn-dyed Fabric Defect Detection with YOLOV2 Based on Deep Convolution Neural Networks_2018

• Mobile-Unet: An efficient convolutional neural network for fabric defect detection_2020

• Fabric defect detection based on a deep convolutional neural network using a two-stage strategy_2020

• Automatic fabric defect detection using a wide-and-light network_2021

• Fabric Defect Detection Based on Cascade Faster R-CNN_2020

• Exploring Faster RCNN for Fabric Defect Detection_2020

• Automatic fabric defect detection with a wide-and-compact network_2018

• Automatic Fabric Defect Detection Method Using PRAN-Net_2020

• D4Net: De-deformation defect detection network for non-rigid products with large patterns_2020

• EDDs: A series of Efficient Defect Detectors for fabric quality inspection_2020

Reading List

Severstal STEEL: [Link]

1. Defect Detection

   • Mixed supervision for surface-defect detection: from weakly to fully supervised learning (AP=98.74) [Paper] [Code]

   • End-to-end training of a two-stage neural network for defect detection (AP=98.74) [Paper] [Code]

   • 
     

KolektorSDD: [Link]

1. Defect Detection

   • Mixed supervision for surface-defect detection: from weakly to fully supervised learning (AP=100.0) [Paper] [Code]

   • End-to-end training of a two-stage neural network for defect detection (AP=100.0) [Paper] [Code]

   • Segmentation-Based Deep-Learning Approach for Surface-Defect Detection (AP=99.9) [Paper] [Code]

2. Unsupervised Anomaly Detection:

   • Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation (AUROC=0.960) [Paper] [Code]

3. Weakly Supervised Defect Detection:

   • Mixed supervision for surface-defect detection: from weakly to fully supervised learning (AP=93.43) [Paper] [Code]

KolektorSDD2: [Link]

1. Defect Detection

   • Mixed supervision for surface-defect detection: from weakly to fully supervised learning (AP=95.4) [Paper] [Code]

2. Unsupervised Anomaly Detection:

   • Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation (AUROC=0.981) [Paper] [Code]

3. Weakly Supervised Defect Detection:

   • Mixed supervision for surface-defect detection: from weakly to fully supervised learning (AP=73.3) [Paper] [Code]

MVTecAD (MVTEC ANOMALY DETECTION DATASET): [Link] [Paper]

1. Anamoly Detection

   • Towards Total Recall in Industrial Anomaly Detection_2021 [Paper] [Code] 

   • PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization_2020 [Paper] [Code] 

   • CutPaste: Self-Supervised Learning for Anomaly Detection and Localization_CVPR_2021 [Paper] [Code] 

   • Inpainting Transformer for Anomaly Detection_2021 [Paper] 

   • Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detection_2020 [Paper] [Code] 

   • Student-Teacher Feature Pyramid Matching for Unsupervised Anomaly Detection_2021 [Paper] [Code]

   • Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows_2020 [Paper] [Code]

   • DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentation_2020 [Paper] [Code]

   • Unsupervised Anomaly Detection with Multi-scale Interpolated Gaussian Descriptors_2021 [Paper] [Code]

   • Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentation_2020 [Paper] [Code]

   • Explainable Deep One-Class Classification_ICLR_2021 [Paper] [Code]

   • MOCCA: Multi-Layer One-Class ClassificAtion for Anomaly Detection_2020 [Paper] [Code]

   • Mean-Shifted Contrastive Loss for Anomaly Detection_2021 [Paper] [Code]

   • Learning and Evaluating Representations for Deep One-class Classification_ICLR_2021 [Paper] [Code]

   • Sub-Image Anomaly Detection with Deep Pyramid Correspondences_2020 [Paper] [Code]

   • Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation_2021 [Paper] [Code]

   • Explainable Deep One-Class Classification_ICLR_2021 [Paper] [Code]

   • Attention Guided Anomaly Localization in Images_ECCV_2020 [Paper] 

   • Reconstruction by Inpainting for Visual Anomaly Detection_2020 [Paper] [Code]

   • Unsupervised Two-Stage Anomaly Detection [Paper]

   • MLF-SC: Incorporating multi-layer features to sparse coding for anomaly detection_2021 [Paper] [Code]

   • Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images_ECCV_2020 [Paper] [Code]

   • Towards Visually Explaining Variational Autoencoders_CVPR_2020 [Paper] [Code]

   • Improved anomaly detection by training an autoencoder with skip connections on images corrupted with Stain-shaped noise [Paper] [Code]

   • Multiresolution Knowledge Distillation for Anomaly Detection_CVPR_2021 [Paper] [Code]

   • Anomaly localization by modeling perceptual features_2020 [Paper] [Code]

   • AnomalyHop: An SSL-based Image Anomaly Localization Method_2021 [Paper] [Code]

   • Attribute Restoration Framework for Anomaly Detection_2019 [Paper] [Code]

   • Puzzle-AE: Novelty Detection in Images through Solving Puzzles_2020 [Paper] [Code]

   • Data augmentation and pre-trained networks for extremely low data regimes unsupervised visual inspection_2021 [Paper]

   • Attention Map-guided Two-stage Anomaly Detection using Hard Augmentation_2021 [Paper]

   • Evaluation of Point Pattern Features for Anomaly Detection of Defect within Random Finite Set Framework_2021 [Paper]

   • Few-Shot Defect Segmentation Leveraging Abundant Normal Training Samples Through Normal Background Regularization and Crop-and-Paste Operation_2020 [Paper]

   • AutoOD: Automated Outlier Detection via Curiosity-guided Search and Self-imitation Learning_2020 [Paper]

   • DOC3-Deep One Class Classification using Contradictions_2021 [Paper]

   • Glancing at the Patch: Anomaly Localization With Global and Local Feature Comparison_CVPR_2021 [Paper]

   • Unsupervised Learning of Multi-level Structures for Anomaly Detection_2021 [Paper]

   • Self-Trained One-class Classification for Unsupervised Anomaly Detection_2021 [Paper] 

   • Anomaly Detection By Autoencoder Based On Weighted Frequency Domain Loss_2021 [Paper]

   • Energy-Based Anomaly Detection and Localization_2021 [Paper] 

   • Distance-Based Anomaly Detection for Industrial Surfaces Using Triplet Networks_2020 [Paper]

   • A Unifying Review of Deep and Shallow Anomaly Detection_2020 [Paper] 

   • Contrastive Predictive Coding for Anomaly Detection_2021 [Paper]

   • One-Class Classification: A Survey_2021 [Paper] 

   • Neural Batch Sampling with Reinforcement Learning for Semi-Supervised Anomaly Detection_ECCV_2020 [Paper]

   • Iterative Image Inpainting with Structural Similarity Mask for Anomaly Detection [Paper]

   • Improving unsupervised anomaly localization by applying multi-scale memories to autoencoders [Paper]

DAGM2007: [Link]

1. Defect Detection

   • Mixed supervision for surface-defect detection: from weakly to fully supervised learning (AC=100.0) [Paper] [Code]

   • Auto-Classifier: A Robust Defect Detector Based on an AutoML Head (AC=100.0) [Paper]

   • End-to-end training of a two-stage neural network for defect detection (AP=100.0) [Paper]

2. Weakly Supervised Defect Detection:

   • Mixed supervision for surface-defect detection: from weakly to fully supervised learning (AP=74) [Paper] [Code]

TFT-LCD Array:

Applications

1. DEye (Keep an Eye on Defects Inspection) [Link]

2. IC chip defect inspection - iPQ [Link]

3. Defect detection of roads infrastructure -Eyevi [Link]

4. AI Inspect Visual Defect Detection [Link]

5. AI.SEE™ – Automated Quality Assurance using AI driven Image Recognition [Link]

6. Highway road crack damage inspection

7. Inspection of defects in braid

8. Cover slip inspection

9. Defect detection of civil infrastructure

10. Power line crack detection

11. Others: metal surfaces, LCD screens, buildings, power lines and other defects or abnormal inspection objects. 

12. Mitutoyo Launch AI Inspect Visual Defect Detection Software [Link]

13. Industrial Visual Defect Inspection of Electronic Components with Siamese Neural Network

14. Robotic Defect Inspection with Visual and Tactile Perception for Large-scale Components

15. A Cascaded Insulator Defect Detection Model Combining Semantic Segmentation and Object Detection

16. UN-YOLOv5s: A UAV-Based Aerial Photography Detection Algorithm

17. Steel surface defect detection based on improved CenterNet algorithm

18. Defect inspection in semiconductor images using statistical methods and neural networks

19. Research on steel surface defect detection based on YOLOv5

20. YOLO-Xray: A Bubble Defect Detection Algorithm for Chip X-ray Images Based on Improved YOLOv5

21. A Dynamic Weights-Based Wavelet Attention Neural Network for Defect Detection

22. A Small-Sized Defect Detection Method for Overhead Transmission Lines Based on Convolutional Neural Networks

23. Insu-YOLO: An Insulator Defect Detection Algorithm Based on Multiscale Feature Fusion

24. Multiscale Attention Networks for Pavement Defect Detection

25. YOLO-CEA: a real-time industrial defect detection method based on contextual enhancement and attention

26. "Light-YOLOv5: A Lightweight Algorithm for Improved YOLOv5 in Complex Fire Scenarios"

Similar Methods

• [AIT] DJ Chen, HY Hsieh, TL Liu, "Adaptive Image Transformer for One-Shot Object Detection", Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12247-12256, 2021.

• An End-to-End Steel Surface Defect Detection Approach via Fusing Multiple Hierarchical Features.

• Unifying Deep Local and Global Features for Image Search"

• "Stochastic Multiple Target Sampling Gradient Descent" (Using KL, multitask)

Detection Application

• An in-depth assessment of convolutional neural networks for rail surface defect detection.

• Real-Time Plastic Surface Defect Detection Using Deep Learning

• Weighting model End-to-End Adversarial-Attention Network for Multi-Modal Clustering (having weighing model between multi-modals)

Transformer

• "An end-to-end steel surface defect detection approach via Swin transformer"

• "

Sensor

• "SDDet: An Enhanced Encoder–Decoder Network With Hierarchical Supervision for Surface Defect Detection"