Distance-Based Anomaly Detection for Industrial Surfaces Using Triplet Networks

Tayeh, Tareq; Aburakhia, Sulaiman; Myers, Ryan; Shami, Abdallah

doi:10.48550/arxiv.2011.04121

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Surprisingly, as we will show in Section 4, without the hindsight of knowing this, a deep convolution network does not learn these shortcuts. Using Cutout in the algorithm design for defect detection can also be found in [32,57]. We can make the task harder by randomly choosing colors and the scale as shown in Figure 2(d) to avoid naive shortcut solutions.…”

Section: Self-supervised Learning With Cutpastementioning

confidence: 99%

“…Because of practical applications, such as industrial inspection or medical diagnosis, defect detection [9,5] has received lots of attention. The initial steps have been taken with methods including autoencoding [9,7,25,59], generative adversarial networks [48,3], using pretrained models on ImageNet [38,45,6,14,43,44], and self-supervised learning by solving different proxy tasks with augmentations [61,47,57,15]. The proposed CutPaste prediction task is not only shown to have strong performance on defect detection, but also amenable to combine with existing methods, such as transfer learning from pretrained models for better performance or patch-based models for more accurate localization, which we demonstrate in Section 4.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

CutPaste: Self-Supervised Learning for Anomaly Detection and Localization

Sohn

Yoon

et al. 2021

Preprint

View full text Add to dashboard Cite

We aim at constructing a high performance model for defect detection that detects unknown anomalous patterns of an image without anomalous data. To this end, we propose a two-stage framework for building anomaly detectors using normal training data only. We first learn self-supervised deep representations and then build a generative one-class classifier on learned representations. We learn representations by classifying normal data from the CutPaste, a simple data augmentation strategy that cuts an image patch and pastes at a random location of a large image. Our empirical study on MVTec anomaly detection dataset demonstrates the proposed algorithm is general to be able to detect various types of real-world defects. We bring the improvement upon previous arts by 3.1 AUCs when learning representations from scratch. By transfer learning on pretrained representations on ImageNet, we achieve a new state-of-theart 96.6 AUC. Lastly, we extend the framework to learn and extract representations from patches to allow localizing defective areas without annotations during training.

show abstract

Section: Self-supervised Learning With Cutpastementioning

confidence: 99%