Inpainting Transformer for Anomaly Detection

Pirnay, Jonathan; Chai, Keng Yip

doi:10.48550/arxiv.2104.13897

Cited by 10 publications

(18 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RIAD [90] proposes to mitigate this effect by inputting merely partial image, in conjunction with the use of a newly proposed image similarity metric function, as an image restoration problem. ITAD [91] transforms anomaly detection task into a patch sequence inpainting problem based on self-attention. Meanwhile, to compensate for the disadvantage that this type of method is difficult to cover larger anomaly regions, the transformer network is proposed to reconstruct only the covered patches, and local and global embedding methods are designed for different cases.…”

Section: Reconstruction Based Methodsmentioning

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

Section: Reconstruction Based Methodsmentioning

confidence: 99%

A Survey on Unsupervised Industrial Anomaly Detection Algorithms

Cui¹,

Liu²,

Lian³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…AUC skipGAN [21] 55.1 Puzzle AE [61] 55.4 DifferNet [39] 84.9 InTra [62] 70.1 CutPaste [14] 60.2 Draem [19] 85.9 Ours 91.4…”

Section: Methodsmentioning

confidence: 99%

Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection

Liang¹,

Zhang²,

Zhao³

et al. 2022

Preprint

View full text Add to dashboard Cite

Density-based and classification-based methods have ruled unsupervised anomaly detection in recent years, while reconstruction-based methods are rarely mentioned for the poor reconstruction ability and low performance. However, the latter requires no costly extra training samples for the unsupervised training that is more practical, so this paper focuses on improving this kind of method and proposes a novel Omni-frequency Channel-selection Reconstruction (OCR-GAN) network to handle anomaly detection task in a perspective of frequency. Concretely, we propose a Frequency Decoupling (FD) module to decouple the input image into different frequency components and model the reconstruction process as a combination of parallel omnifrequency image restorations, as we observe a significant difference in the frequency distribution of normal and abnormal images. Given the correlation among multiple frequencies, we further propose a Channel Selection (CS) module that performs frequency interaction among different encoders by adaptively selecting different channels. Abundant experiments demonstrate the effectiveness and superiority of our approach over different kinds of methods, e.g., achieving a new state-of-the-art 98.3 detection AUC on the MVTec AD dataset without extra training data that markedly surpasses the reconstruction-based baseline by +38.1↑ and the current SOTA method by +0.3↑. Source code will be available at https://github.com/zhangzjn/OCR-GAN.

show abstract

“…In [19,1], the gradient of a classifier is used to obtain anomaly maps. Recently, transformer networks [21] were also successfully applied on brain anomaly detection [20]. In [15], a new thresholding method is proposed for anomaly segmentation on the BRATS dataset.…”

Section: Related Workmentioning

confidence: 99%

Diffusion Models for Medical Anomaly Detection

Wolleb¹,

Bieder²,

Sandkühler³

et al. 2022

Preprint

View full text Add to dashboard Cite

In medical applications, weakly supervised anomaly detection methods are of great interest, as only image-level annotations are required for training. Current anomaly detection methods mainly rely on generative adversarial networks or autoencoder models. Those models are often complicated to train or have difficulties to preserve fine details in the image. We present a novel weakly supervised anomaly detection method based on denoising diffusion implicit models. We combine the deterministic iterative noising and denoising scheme with classifier guidance for image-to-image translation between diseased and healthy subjects. Our method generates very detailed anomaly maps without the need for a complex training procedure. We evaluate our method on the BRATS2020 dataset for brain tumor detection and the CheXpert dataset for detecting pleural effusions.

show abstract

Inpainting Transformer for Anomaly Detection

Cited by 10 publications

References 32 publications

A Survey on Unsupervised Industrial Anomaly Detection Algorithms

A Survey on Unsupervised Industrial Anomaly Detection Algorithms

Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection

Diffusion Models for Medical Anomaly Detection

Contact Info

Product

Resources

About