Anomaly Detection via Reverse Distillation from One-Class Embedding

Deng, Hanqiu; Li, Xingyu

doi:10.48550/arxiv.2201.10703

Cited by 4 publications

(4 citation statements)

References 31 publications

(87 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in figure 8 and table 2, the ROC as well as AUROC metrics of CFlow [32], PaDim [33], FastFlow [34], Reverse Distillation [35], DRAM [36], STFPM [37] and PatchCore used in this paper were compared.…”

Section: Results and Analysismentioning

confidence: 99%

Outer surface defect detection of steel pipes with 3D vision based on multi-line structured lights

Jin,

Li,

Qin

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Surface defects pose a significant threat to the quality of cold rolled seamless steel pipes. Despite the efficacy of current vision-based deep learning techniques, they struggle to accurately differentiate pseudo-defects that lack depth. To overcome this obstacle, we have designed a novel visual detection system specifically for identifying surface defects on steel pipes. This system is inspired by laser triangulation and compensates for the absence of depth information in 2D images by leveraging the shape alterations of a multilinear structured light bar projected onto the steel pipe’s surface. Addressing the challenge of acquiring evenly distributed and difficult-to-obtain defect samples in real-world production processes, we have incorporated an unsupervised anomaly detection network, PatchCore, into the system.The proposed method achieves an area under the receiver operating characteristic curve (AUROC) of 99.84% and an F1 score of 0.9778 on a dataset collected and labeled at an industrial site. Furthermore, the online detection system has been successfully integrated into a cold rolled steel pipe production line, underscoring its practical applicability.

show abstract

Section: Results and Analysismentioning

confidence: 99%

Outer surface defect detection of steel pipes with 3D vision based on multi-line structured lights

Jin,

Li,

Qin

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…For MVTec AD dataset for 2D task, we report the performance comparison of Glance [31], DRAEM [35], DFR [32], R-D [9], PaDim [8], P-SVDD [33], FYD [37], SPADE [7], PANDA [20], CutPaste [18], NSA [28], CFlow [14], FastFlow [34], PatchCore [22] in terms of the image-level and pixel-level metrics. The inference efficiencies of some of these methods are also provided.…”

Section: Resultsmentioning

confidence: 99%

Benchmarking Unsupervised Anomaly Detection and Localization

Zheng¹,

Wang²,

Qian³

et al. 2022

Preprint

View full text Add to dashboard Cite

Unsupervised anomaly detection and localization, as of one the most practical and challenging problems in computer vision, has received great attention in recent years. From the time the MVTec AD dataset was proposed to the present, new research methods that are constantly being proposed push its precision to saturation. It is the time to conduct a comprehensive comparison of existing methods to inspire further research. This paper extensively compares 13 papers in terms of the performance in unsupervised anomaly detection and localization tasks, and adds a comparison of inference efficiency previously ignored by the community. Meanwhile, analysis of the MVTec AD dataset are also given, especially the label ambiguity that affects the model fails to achieve full marks. Moreover, considering the proposal of the new MVTec 3D-AD dataset, this paper also conducts experiments using the existing state-of-the-art 2D methods on this new dataset, and reports the corresponding results with analysis.

show abstract

“…Knowledge distillation-based anomaly detection is a newer deep learning method for anomaly detection [24,25]. It uses a teacher-student model to achieve the goal of unsupervised defect detection.…”

Section: Knowledge Distillation-based Anomaly Detectionmentioning

confidence: 99%

Industrial anomaly detection with multiscale autoencoder and deep feature extractor‐based neural network

Tang

Hsu²,

2023

IET Image Processing

View full text Add to dashboard Cite

With the maturity of deep learning image recognition technology and the popularity of automated production lines, deep learning industrial anomaly detection has become an important research topic in recent years. In this study, an anomaly detection model with a multi‐scale autoencoder and deep feature extractor is proposed. This model was confirmed to obtain the highest area under the curve (AUC) in 14 of the 17 industrial detection tasks. In addition, the receiver operating characteristic (ROC) curves show that an appropriate threshold of the proposed model exists, which can achieve a low false‐positive rate and maintain a high true‐positive rate. Furthermore, the influence of different feature extractors on the method is discussed. It was shown that the proposed method can maintain good detection ability with most of the feature extractor. Therefore, it is suitable for industrial optical inspection systems with different hardware conditions.

show abstract

Anomaly Detection via Reverse Distillation from One-Class Embedding

Cited by 4 publications

References 31 publications

Outer surface defect detection of steel pipes with 3D vision based on multi-line structured lights

Outer surface defect detection of steel pipes with 3D vision based on multi-line structured lights

Benchmarking Unsupervised Anomaly Detection and Localization

Industrial anomaly detection with multiscale autoencoder and deep feature extractor‐based neural network

Contact Info

Product

Resources

About