CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows

Gudovskiy, Denis; Ishizaka, Shun; Kozuka, Kazuki

doi:10.1109/wacv51458.2022.00188

Cited by 304 publications

(164 citation statements)

References 22 publications

Supporting

Mentioning

163

Contrasting

Order By: Relevance

“…Also, even in the aspect of P-AUROC, which is an evaluation metric for pixel-level anomaly localization, the proposed method achieved SOTA performance for object classes. But, the proposed method has slightly lower performance than CFLOW [8] in terms of P-AUROC when all classes are considered. Nonetheless, while the conventional methods show strength only in a one of anomaly detection and localization, the proposed method guarantees excellent performance in both scenarios.…”

Section: Quantitative Resultsmentioning

confidence: 84%

CFA: Coupled-Hypersphere-Based Feature Adaptation for Target-Oriented Anomaly Localization

2022

View full text Add to dashboard Cite

For a long time, anomaly localization has been widely used in industries. Previous studies focused on approximating the distribution of normal features without adaptation to a target dataset. However, since anomaly localization should precisely discriminate normal and abnormal features, the absence of adaptation may make the normality of abnormal features overestimated. Thus, we propose Coupled-hypersphere-based Feature Adaptation (CFA) which accomplishes sophisticated anomaly localization using features adapted to the target dataset. CFA consists of (1) a learnable patch descriptor that learns and embeds target-oriented features and (2) scalable memory bank independent of the size of the target dataset. And, CFA adopts transfer learning to increase the normal feature density so that abnormal features can be clearly distinguished by applying patch descriptor and memory bank to a pretrained CNN. The proposed method outperforms the previous methods quantitatively and qualitatively. For example, it provides an AUROC score of 99.5% in anomaly detection and 98.5% in anomaly localization of MVTec AD benchmark. In addition, this paper points out the negative effects of biased features of pre-trained CNNs and emphasizes the importance of the adaptation to the target dataset. The code is publicly available at https://github.com/ sungwool/CFA_for_anomaly_localization

show abstract

Section: Quantitative Resultsmentioning

confidence: 84%

CFA: Coupled-Hypersphere-Based Feature Adaptation for Target-Oriented Anomaly Localization

2022

View full text Add to dashboard Cite

show abstract

“…The included generative models in Fig. 4 are AnoGAN [31], LSA [130], GANomaly [131], AGAN [45], Normalizing Flowsbased DifferNet [132], CFLOW [133] and CS-Flow [134].…”

Section: Comparative Evaluation and Discussionmentioning

confidence: 99%

Self-Supervised Anomaly Detection: A Survey and Outlook

Hojjati¹,

Ho²,

Armanfard³

2022

Preprint

View full text Add to dashboard Cite

Over the past few years, anomaly detection, a subfield of machine learning that is mainly concerned with the detection of rare events, witnessed an immense improvement following the unprecedented growth of deep learning models. Recently, the emergence of self-supervised learning has sparked the development of new anomaly detection algorithms that surpassed state-of-the-art accuracy by a significant margin. This paper aims to review the current approaches in self-supervised anomaly detection. We present technical details of the common approaches and discuss their strengths and drawbacks. We also compare the performance of these models against each other and other state-of-the-art anomaly detection models. Finally, we discuss a variety of new directions for improving the existing algorithms. 1

show abstract

“…There are methods [85,86] adopting normalizing flow [121] to estimate distribution through a trainable process that maximizes the log-likelihood of normal image features. Normal image features are embedded into standard normal distribution and the probability is used to identify and locate anomalies.…”

Section: Normalizing Flow (Nf) Based Methodsmentioning

confidence: 99%

“…To our best knowledge, no review has been done for the recently emerged unsupervised methods. The article will provide a comprehensive and in-depth summary of the state-of-the-art algorithms for industrial anomaly detection, which will be divided into five categories listed as 4.1 Normalizing Flow (NF) based [85][86][87][88] [103,[110][111][112]. This comprehensive summary is expected to contribute to the implementation and practice of industrial field.…”

Section: Related Workmentioning

confidence: 99%

A Survey on Unsupervised Industrial Anomaly Detection Algorithms

Cui¹,

Liu²,

Lian³

2022

Preprint

View full text Add to dashboard Cite

In line with the development of Industry 4.0, more and more attention is attracted to the field of surface defect detection. Improving efficiency as well as saving labor costs has steadily become a matter of great concern in industry field, where deep learning-based algorithms performs better than traditional vision inspection methods in recent years. While existing deep learning-based algorithms are biased towards supervised learning, which not only necessitates a huge amount of labeled data and a significant amount of labor, but it is also inefficient and has certain limitations. In contrast, recent research shows that unsupervised learning has great potential in tackling above disadvantages for visual anomaly detection. In this survey, we summarize current challenges and provide a thorough overview of recently proposed unsupervised algorithms for visual anomaly detection covering five categories, whose innovation points and frameworks are described in detail. Meanwhile, information on publicly available datasets containing surface image samples are provided. By comparing different classes of methods, the advantages and disadvantages of anomaly detection algorithms are summarized. It is expected to assist both the research community and industry in developing a broader and cross-domain perspective.

show abstract

CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows

Cited by 304 publications

References 22 publications

CFA: Coupled-Hypersphere-Based Feature Adaptation for Target-Oriented Anomaly Localization

CFA: Coupled-Hypersphere-Based Feature Adaptation for Target-Oriented Anomaly Localization

Self-Supervised Anomaly Detection: A Survey and Outlook

A Survey on Unsupervised Industrial Anomaly Detection Algorithms

Contact Info

Product

Resources

About