Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows

Rudolph, Marco; Wandt, Bastian; Rosenhahn, Bodo

doi:10.1109/wacv48630.2021.00195

Cited by 241 publications

(179 citation statements)

References 11 publications

Supporting

Mentioning

142

Contrasting

Order By: Relevance

“…We also study industrial anomaly detection on more specialized tasks. For that, we leverage the Magnetic Tile Defects (MTD) [26] dataset as used in [42], which contains 925 defect-free and 392 anomalous magnetic tile images with varied illumination levels and image sizes. Same as in [42], 20% of defect-free images are evaluated against at test time, with the rest used for cold-start training.…”

Section: Methodsmentioning

confidence: 99%

“…To encourage better estimation of the nominal feature distribution, extensions based on Gaussian mixture models [60], generative adversarial training objectives [39,2,43], invariance towards predefined physical augmentations [25], robustness of hidden features to reintroduction of reconstructions [29], prototypical memory banks [21], attention-guidance [52], structural objectives [59,7] or constrained representation spaces [38] have been pro-posed. Other unsupervised representation learning methods can similarly be utilised, such as via GANs [13], learning to predict predefined geometric transformations [20] or via normalizing flows [42]. Given respective nominal representations and novel test representations, anomaly detection can then be a simple matter of reconstruction errors [44], distances to k nearest neighbours [18] or finetuning of a one-class classification model such as OC-SVMs [46] or SVDD [50,56] on top of these features.…”

Section: Related Workmentioning

confidence: 99%

“…Given respective nominal representations and novel test representations, anomaly detection can then be a simple matter of reconstruction errors [44], distances to k nearest neighbours [18] or finetuning of a one-class classification model such as OC-SVMs [46] or SVDD [50,56] on top of these features. For the majority of these approaches, anomaly localization comes naturally based on pixel-wise reconstruction errors, saliency-based approaches such as GradCAM [47] or XRAI [28] can be used for anomaly segmentation [52,42,45] as well.…”

Section: Related Workmentioning

confidence: 99%

“…To better account for the distribution shift between natural pretraining and industrial image data, subsequent adaptation can be done, e.g. via student-teacher knowledge distillation [24] such as in [6,45] or normalizing flows [17,30] trained on top of pretrained network features [42].…”

Section: Related Workmentioning

confidence: 99%

“…Existing work on cold-start, industrial visual anomaly detection relies on learning a model of the nominal distribution via auto-encoding methods [44,36,12], GANs [2,39,43], or other unsupervised adaptation methods [56,42]. Recently, Bergman et al [4] and Cohen et al [10] proposed models that build on common deep representations from ImageNet classification without adaptation to the target distribution.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Towards Total Recall in Industrial Anomaly Detection

Roth¹,

Pemula²,

Zepeda³

et al. 2021

Preprint

View full text Add to dashboard Cite

Being able to spot defective parts is a critical component in large-scale industrial manufacturing. A particular challenge that we address in this work is the cold-start problem: fit a model using nominal (non-defective) example images only. While handcrafted solutions per class are possible, the goal is to build systems that work well simultaneously on many different tasks automatically. The best peforming approaches combine embeddings from ImageNet models with an outlier detection model. In this paper, we extend on this line of work and propose PatchCore, which uses a maximally representative memory bank of nominal patchfeatures. PatchCore offers competitive inference times while achieving state-of-the-art performance for both detection and localization. On the standard dataset MVTec AD Patch-Core achieves an image-level anomaly detection AUROC score of 99.1%, more than halving the error compared to the next best competitor. We further report competitive results on two additional datasets and also find competitive results in the few samples regime. * Work done during an internship at Amazon Tübingen.1 Commonly also dubbed one-class classification (OCC).

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Towards Total Recall in Industrial Anomaly Detection

Roth¹,

Pemula²,

Zepeda³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

RDAD: A reconstructive and discriminative anomaly detection model based on transformer

Xie

Huang

Ning

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

Given the shortcomings of low detection accuracy and poor generalization performance of most current surface defect detection methods for industrial products, this paper proposes a reconstructive and discriminative anomaly detection model. The proposed method uses squeeze-and-excitation block to assign the attention of feature channels to enhance the sensitivity of related features and improve the ability of the model to learn normal and anomaly boundaries. In addition, channel transformer is introduced in the encoder-decoder, so that the decoder better fuses the features in the encoder and reduces the semantic gap, and enhances the segmentation ability of anomalous regions of the model. The model is only trained with normal samples, and completes the localization of anomalous regions while detecting anomalies. Experiments are conducted on the challenging MVTec anomaly detection and Magnetic Tile Defect data sets. Compared with the current state-of-the-art unsupervised anomaly detection methods, the model not only improves the accuracy of anomaly detection, but also has better generality.

show abstract

DSR – A Dual Subspace Re-Projection Network for Surface Anomaly Detection

Zavrtanik

Kristan

Skočaj

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

RGB-based surface anomaly detection methods have advanced significantly. However, certain surface anomalies remain practically invisible in RGB alone, necessitating the incorporation of 3D information. Existing approaches that employ point-cloud backbones suffer from suboptimal representations and reduced applicability due to slow processing. Re-training RGB backbones, designed for faster dense input processing, on industrial depth datasets is hindered by the limited availability of sufficiently large datasets. We make several contributions to address these challenges. (i) We propose a novel Depth-Aware Discrete Autoencoder (DADA) architecture, that enables learning a general discrete latent space that jointly models RGB and 3D data for 3D surface anomaly detection. (ii) We tackle the lack of diverse industrial depth datasets by introducing a simulation process for learning informative depth features in the depth encoder. (iii) We propose a new surface anomaly detection method 3DSR, which outperforms all existing state-of-theart on the challenging MVTec3D anomaly detection benchmark, both in terms of accuracy and processing speed. The experimental results validate the effectiveness and efficiency of our approach, highlighting the potential of utilizing depth information for improved surface anomaly detection. Code

show abstract

Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows

Cited by 241 publications

References 11 publications

Towards Total Recall in Industrial Anomaly Detection

Towards Total Recall in Industrial Anomaly Detection

RDAD: A reconstructive and discriminative anomaly detection model based on transformer

DSR – A Dual Subspace Re-Projection Network for Surface Anomaly Detection

Contact Info

Product

Resources

About