Awesome Industrial Anomaly Detection

We will keep focusing on this field and update relevant information.

Deep Visual Anomaly Detection in Industrial Manufacturing: A Survey

Paper Tree

Timeline

Paper list for industrial image anomaly detection

1 Introduction

(yang2021generalized)Generalized out-of-distribution detection: A survey [2021]
(bergmann2019mvtec)MVTec AD: A comprehensive real-world dataset for unsupervised anomaly detection [2019]
(bergmann2021mvtec)The MVTec Anomaly Detection Dataset: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection [2021]
(czimmermann2020visual)Visual-based defect detection and classification approaches for industrial applications: a survey [2020]
(tao2022deep)Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey [2022]
(cui2022survey)A Survey on Unsupervised Industrial Anomaly Detection Algorithms [2022]
A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure [2015]

2 Unsupervised AD

2.1 Feature-Embedding-based Methods

2.1.1 Teacher-Student

(bergmann2020uninformed)Uninformed students: Student-teacher anomaly detection with discriminative latent embeddings [2020]
(Wang2021StudentTeacherFP)Student-Teacher Feature Pyramid Matching for Anomaly Detection [2021]
(salehi2021multiresolution)Multiresolution knowledge distillation for anomaly detection [2020]
(yamada2021reconstruction)Reconstruction Student with Attention for Student-Teacher Pyramid Matching [2021]
(yamada2022reconstructed)Reconstructed Student-Teacher and Discriminative Networks for Anomaly Detection [2022]
(deng2022anomaly)Anomaly Detection via Reverse Distillation from One-Class Embedding [2022]
(rudolph2022asymmetric)Asymmetric Student-Teacher Networks for Industrial Anomaly Detection [2022]
(cao2022informative)Informative knowledge distillation for image anomaly segmentation [2022]

2.1.2 One-Class Classification (OCC)

(yi2020patch)Patch svdd: Patch-level svdd for anomaly detection and segmentation [2020]
(zhang2021anomaly)Anomaly detection using improved deep SVDD model with data structure preservation [2021]
(hu2021semantic)A Semantic-Enhanced Method Based On Deep SVDD for Pixel-Wise Anomaly Detection [2021]
(massoli2021mocca)MOCCA: Multilayer One-Class Classification for Anomaly Detection [2021]
(sauter2021defect)Defect Detection of Metal Nuts Applying Convolutional Neural Networks [2021]
(reiss2021panda)Panda: Adapting pretrained features for anomaly detection and segmentation [2021]
(reiss2021mean)Mean-shifted contrastive loss for anomaly detection [2021]
(sohn2020learning)Learning and Evaluating Representations for Deep One-Class Classification [2020]
(yoa2021self)Self-supervised learning for anomaly detection with dynamic local augmentation [2021]
(de2021contrastive)Contrastive Predictive Coding for Anomaly Detection [2021]
(li2021cutpaste)Cutpaste: Self-supervised learning for anomaly detection and localization [2021]
(iquebal2020consistent)Consistent estimation of the max-flow problem: Towards unsupervised image segmentation [2020]
(yang2022memseg)MemSeg: A semi-supervised method for image surface defect detection using differences and commonalities [2022]

2.1.3 Distribution-Map

(tailanian2021multi)A Multi-Scale A Contrario method for Unsupervised Image Anomaly Detection [2021]
(rippel2021modeling)Modeling the distribution of normal data in pre-trained deep features for anomaly detection [2021]
(rippel2021transfer)Transfer Learning Gaussian Anomaly Detection by Fine-Tuning Representations [2021]
(zhang2022pedenet)PEDENet: Image anomaly localization via patch embedding and density estimation [2022]
(wan2022unsupervised)Unsupervised image anomaly detection and segmentation based on pre-trained feature mapping [2022]
(wan2022position)Position Encoding Enhanced Feature Mapping for Image Anomaly Detection [2022]
(zheng2022focus)Focus your distribution: Coarse-to-fine non-contrastive learning for anomaly detection and localization [2022]
(yu2021fastflow)Fastflow: Unsupervised anomaly detection and localization via 2d normalizing flows [2021]
(rudolph2021same)Same same but differnet: Semi-supervised defect detection with normalizing flows [2021]
(rudolph2022fully)Fully convolutional cross-scale-flows for image-based defect detection [2022]
(gudovskiy2022cflow)Cflow-ad: Real-time unsupervised anomaly detection with localization via conditional normalizing flows [2022]
(yan2022cainnflow)CAINNFlow: Convolutional block Attention modules and Invertible Neural Networks Flow for anomaly detection and localization tasks [2022]
(kim2022altub)AltUB: Alternating Training Method to Update Base Distribution of Normalizing Flow for Anomaly Detection [2022]

2.1.4 Memory Bank

(cohen2020sub)Sub-image anomaly detection with deep pyramid correspondences [2020]
(kim2021semi)Semi-orthogonal embedding for efficient unsupervised anomaly segmentation [2021]
(li2021anomaly)Anomaly Detection Via Self-Organizing Map [2021]
(wan2021industrial)Industrial Image Anomaly Localization Based on Gaussian Clustering of Pretrained Feature [2021]
(roth2022towards)Towards total recall in industrial anomaly detection[2022]
(Lee2022CFACF)CFA: Coupled-Hypersphere-Based Feature Adaptation for Target-Oriented Anomaly Localization[2022]
(kim2022fapm)FAPM: Fast Adaptive Patch Memory for Real-time Industrial Anomaly Detection[2022]
(jang2022n)N-pad: Neighboring Pixel-based Industrial Anomaly Detection [2022]
(bae2022image)Image Anomaly Detection and Localization with Position and Neighborhood Information [2022]
(tsai2022multi)Multi-scale patch-based representation learning for image anomaly detection and segmentation [2022]
(zou2022spot)SPot-the-Difference Self-supervised Pre-training for Anomaly Detection and Segmentation [2022]

2.2 Reconstruction-Based Methods

2.2.1 Autoencoder (AE)

(bergmann2018improving)Improving unsupervised defect segmentation by applying structural similarity to autoencoders [2018]
(chung2020unsupervised)Unsupervised anomaly detection using style distillation [2020]
(liu2021unsupervised)Unsupervised two-stage anomaly detection [2021]
(yang2020dfr)Dfr: Deep feature reconstruction for unsupervised anomaly segmentation [2020]
(yan2021unsupervised)Unsupervised anomaly segmentation via multilevel image reconstruction and adaptive attention-level transition [2021]
(zhou2020encoding)Encoding structure-texture relation with p-net for anomaly detection in retinal images [2020]
(collin2021improved)Improved anomaly detection by training an autoencoder with skip connections on images corrupted with stain-shaped noise [2021]
(tao2022unsupervised)Unsupervised anomaly detection for surface defects with dual-siamese network [2022]
(hou2021divide)Divide-and-assemble: Learning block-wise memory for unsupervised anomaly detection [2021]
(liu2022reconstruction)Reconstruction from edge image combined with color and gradient difference for industrial surface anomaly detection [2022]
(kim2022spatial)Spatial Contrastive Learning for Anomaly Detection and Localization [2022]
(li2020superpixel)Superpixel masking and inpainting for self-supervised anomaly detection [2020]
(nakanishi2020iterative)Iterative image inpainting with structural similarity mask for anomaly detection [2020]
(huang2022self)Self-Supervised Masking for Unsupervised Anomaly Detection and Localization [2022]
(zavrtanik2021reconstruction)Reconstruction by inpainting for visual anomaly detection [2021]
(zavrtanik2021draem)Draem-a discriminatively trained reconstruction embedding for surface anomaly detection [2021]
(zavrtanik2022dsr)DSR: A dual subspace re-projection network for surface anomaly detection [2022]
(schluter2022natural)Natural Synthetic Anomalies for Self-supervised Anomaly Detection and Localization [2022]
(bauer2022self)Self-Supervised Training with Autoencoders for Visual Anomaly Detection [2022]
(ristea2022self)Self-supervised predictive convolutional attentive block for anomaly detection [2022]
(madan2022self)Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection [2022]
(dehaene2019iterative)Iterative energy-based projection on a normal data manifold for anomaly localization [2019]
(liu2020towards)Towards visually explaining variational autoencoders [2020]
(matsubara2020deep)Deep generative model using unregularized score for anomaly detection with heterogeneous complexity [2020]
(dehaene2020anomaly)Anomaly localization by modeling perceptual features [2020]
(wang2020image)Image anomaly detection using normal data only by latent space resampling [2020]

2.2.2 Generative Adversarial Networks (GANs)

(yan2021learning)Learning semantic context from normal samples for unsupervised anomaly detection [2021]
(song2021anoseg)Anoseg: Anomaly segmentation network using self-supervised learning [2021]
(liang2022omni)Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection [2022]

2.2.3 Transformer

(mishra2021vt)VT-ADL: A vision transformer network for image anomaly detection and localization [2021]
(you2022adtr)ADTR: Anomaly Detection Transformer with Feature Reconstruction [2022]
(lee2022anovit)AnoViT: Unsupervised Anomaly Detection and Localization With Vision Transformer-Based Encoder-Decoder [2022]
(mathian2022haloae)HaloAE: An HaloNet based Local Transformer Auto-Encoder for Anomaly Detection and Localization [2022]
(pirnay2022inpainting)Inpainting transformer for anomaly detection [2022]
(jiang2022masked)Masked Swin Transformer Unet for Industrial Anomaly Detection [2022]
(de2022masked)Masked Transformer for image Anomaly Localization [2022]

2.2.4 Diffusion Model

(ho2020denoising)Denoising diffusion probabilistic models [2020]
(wyatt2022anoddpm)AnoDDPM: Anomaly Detection With Denoising Diffusion Probabilistic Models Using Simplex Noise [2022]
(teng2022unsupervised)Unsupervised Visual Defect Detection with Score-Based Generative Model[2022]

2.3 Supervised AD

(chu2020neural)Neural batch sampling with reinforcement learning for semi-supervised anomaly detection [2020]
(liznerski2020explainable)Explainable Deep One-Class Classification [2020]
(venkataramanan2020attention)Attention guided anomaly localization in images [2020]
(bovzivc2021mixed)Mixed supervision for surface-defect detection: From weakly to fully supervised learning [2021]
(pang2021explainable)Explainable deep few-shot anomaly detection with deviation networks [2021]
(wan2022logit)Logit Inducing With Abnormality Capturing for Semi-Supervised Image Anomaly Detection [2022]
(ding2022catching)Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection [2022]
(sindagi2017domain)Domain adaptation for automatic OLED panel defect detection using adaptive support vector data description [2017]
(qiu2021effective)An effective framework of automated visual surface defect detection for metal parts [2021]
(bhattacharya2021interleaved)Interleaved Deep Artifacts-Aware Attention Mechanism for Concrete Structural Defect Classification [2021]
(zeng2021reference)Reference-based defect detection network [2021]
(long2021fabric)Fabric defect detection using tactile information [2021]
(hu2020lightweight)A lightweight spatial and temporal multi-feature fusion network for defect detection [2020]
(ferguson2018detection)Detection and segmentation of manufacturing defects with convolutional neural networks and transfer learning [2018]

3 Other Research Direction

3.1 Few-Shot AD

(wu2021learning)Learning unsupervised metaformer for anomaly detection [2021]
(huang2022registration)Registration based few-shot anomaly detection [2022]
(rudolph2021same)Same same but differnet: Semi-supervised defect detection with normalizing flows [2021]
(roth2022towards)Towards total recall in industrial anomaly detection [2022]
(sheynin2021hierarchical)A hierarchical transformation-discriminating generative model for few shot anomaly detection [2021]
(kamoona2021anomaly)Anomaly detection of defect using energy of point pattern features within random finite set framework [2021]
(schwartz2022maeday)MAEDAY: MAE for few and zero shot AnomalY-Detection [2022]

3.2 Noisy AD

(tan2021trustmae)Trustmae: A noise-resilient defect classification framework using memory-augmented auto-encoders with trust regions [2021]
(yoon2021self)Self-Supervise, Refine, Repeat: Improving Unsupervised Anomaly Detection [2021]
(cordier2022data)Data refinement for fully unsupervised visual inspection using pre-trained networks [2022]
(qiu2022latent)Latent Outlier Exposure for Anomaly Detection with Contaminated Data [2022]
(chen2022deep)Deep one-class classification via interpolated gaussian descriptor [2022]
(roth2022towards)Towards total recall in industrial anomaly detection [2022]
(xisoftpatch)SoftPatch: Unsupervised Anomaly Detection with Noisy Data [2020]
(bergmann2019mvtec)MVTec AD: A comprehensive real-world dataset for unsupervised anomaly detection [2019]

3.3 Anomaly Synthetic

(li2021cutpaste)Cutpaste: Self-supervised learning for anomaly detection and localization [2021]
(yang2022memseg)MemSeg: A semi-supervised method for image surface defect detection using differences and commonalities [2022]
(liu2019multistage)Multistage GAN for fabric defect detection [2019]
(rippel2020gan)Gan-based defect synthesis for anomaly detection in fabrics [2020]
(zhu2017unpaired)Unpaired image-to-image translation using cycle-consistent adversarial networks [2017]
(niu2020defect)Defect image sample generation with GAN for improving defect recognition [2020]
(wei2020defective)Defective samples simulation through neural style transfer for automatic surface defect segment [2020]
(wei2020simulation)A simulation-based few samples learning method for surface defect segmentation [2020]
(jain2020synthetic)Synthetic data augmentation for surface defect detection and classification using deep learning [2020]
(wang2021defect)Defect Transfer GAN: Diverse Defect Synthesis for Data Augmentation [2021]
(heusel2017gans)Gans trained by a two time-scale update rule converge to a local nash equilibrium [2017]
(binkowski2018demystifying)Demystifying MMD GANs [2018]
(zhang2021defect)Defect-GAN: High-fidelity defect synthesis for automated defect inspectio [2021]

3.4 3D AD

({bergmann2022beyond)Beyond Dents and Scratches: Logical Constraints in Unsupervised Anomaly Detection and Localization[2022]
(bergmann2022anomaly)Anomaly detection in 3d point clouds using deep geometric descriptors [2022]
(horwitz2022back)Back to the feature: classical 3d features are (almost) all you need for 3D anomaly detection [2022]
(rusu2009fast)Fast point feature histograms (FPFH) for 3D registration [2009]
(roth2022towards)Towards total recall in industrial anomaly detection [2022]
(reiss2022anomaly)Anomaly Detection Requires Better Representations [2022]
(rudolph2022asymmetric)Asymmetric Student-Teacher Networks for Industrial Anomaly Detection [2022]

3.5 Continual AD

(li2022towards)Towards Continual Adaptation in Industrial Anomaly Detection [2022]

3.6 Uniform AD

(you2022unified)A Unified Model for Multi-class Anomaly Detection [2022]

3.7 Logical AD

(bergmann2022beyond)Beyond Dents and Scratches: Logical Constraints in Unsupervised Anomaly Detection and Localization [2022]

4 Dataset

(song2013noise)A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects [2013]
(yang2021deep)Deep learning based steel pipe weld defect detection [2021]
(SDD2019)Severstal: Steel Defect Detection [2019]
(carrera2016defect)Defect detection in SEM images of nanofibrous materials [2016]
(mery2015gdxray)GDXray: The database of X-ray images for nondestructive testing [2015]
(tang2019online)Online PCB defect detector on a new PCB defect dataset [2019]
(tsang2016fabric)Fabric inspection based on the Elo rating method [2016]
(tabernik2020segmentation)Segmentation-based deep-learning approach for surface-defect detection [2020]
(bovzivc2021mixed)Mixed supervision for surface-defect detection: From weakly to fully supervised learning [2021]
(gan2017hierarchical)A hierarchical extractor-based visual rail surface inspection system [2017]
(bonfiglioli2022eyecandies)The Eyecandies Dataset for Unsupervised Multimodal Anomaly Detection and Localization [2022]
(bergmann2019mvtec)MVTec AD: A comprehensive real-world dataset for unsupervised anomaly detection [2019]
(bergmann2021mvtec)The mvtec 3d-ad dataset for unsupervised 3d anomaly detection and localization [2021]
(bergmann2022beyond)Beyond Dents and Scratches: Logical Constraints in Unsupervised Anomaly Detection and Localization [2022]
(jezek2021deep)Deep learning-based defect detection of metal parts: evaluating current methods in complex conditions [2021]
(mishra2021vt)VT-ADL: A vision transformer network for image anomaly detection and localization [2021]
(zou2022spot)SPot-the-Difference Self-supervised Pre-training for Anomaly Detection and Segmentation [2022]
(huang2020surface)Surface defect saliency of magnetic tile [2020]
(DAGMGNSS2077)DAGM dataset [2000]

lizhuo97 / awesome-industrial-anomaly-detection Goto Github PK

awesome-industrial-anomaly-detection's Introduction

Awesome Industrial Anomaly Detection

Paper Tree

Timeline

1 Introduction

2 Unsupervised AD

2.1 Feature-Embedding-based Methods

2.1.1 Teacher-Student

2.1.2 One-Class Classification (OCC)

2.1.3 Distribution-Map

2.1.4 Memory Bank

2.2 Reconstruction-Based Methods

2.2.1 Autoencoder (AE)

2.2.2 Generative Adversarial Networks (GANs)

2.2.3 Transformer

2.2.4 Diffusion Model

2.3 Supervised AD

3 Other Research Direction

3.1 Few-Shot AD

3.2 Noisy AD

3.3 Anomaly Synthetic

3.4 3D AD

3.5 Continual AD

3.6 Uniform AD

3.7 Logical AD

4 Dataset

awesome-industrial-anomaly-detection's People

Contributors

Recommend Projects

Recommend Topics

Recommend Org