Data augmentation and pre-trained networks for extremely low data regimes unsupervised visual inspection

Abstract

The use of deep features coming from pre-trained neural networks for unsupervised anomaly detection purposes has recently gathered momentum in the computer vision field. In particular, industrial inspection applications can take advantage of such features, as demonstrated by the multiple successes of related methods on the MVTec Anomaly Detection (MVTec AD) dataset. These methods make use of neural networks pre-trained on auxiliary classification tasks such as ImageNet. However, to our knowledge, no comparative study of robustness to the low data regimes between these approaches has been conducted yet. For quality inspection applications, the handling of limited sample sizes may be crucial as large quantities of images are not available for small series. In this work, we aim to compare three approaches based on deep pre-trained features when varying the quantity of available data in MVTec AD: KNN, Mahalanobis, and PaDiM. We show that although these methods are mostly robust to small sample sizes, they still can benefit greatly from using data augmentation in the original image space, which allows to deal with very small production runs.

arXiv comment16 pages, 8 figures, 9 tables, SPIE proceedings of Optical Metrology conference (https://spie.org/conferences-and-exhibitions/optical-metrology)

References in corpus (17)

• Scikit-learn: Machine Learning in Python
• Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings
• An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
• Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders
• Deep Anomaly Detection with Outlier Exposure
• Deep Anomaly Detection Using Geometric Transformations
• Sub-Image Anomaly Detection with Deep Pyramid Correspondences
• CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances
• Deep Nearest Neighbor Anomaly Detection
• Explainable Deep One-Class Classification
• Classification-Based Anomaly Detection for General Data
• Attribute Restoration Framework for Anomaly Detection
• Why is the Mahalanobis Distance Effective for Anomaly Detection?
• Rethinking Assumptions in Deep Anomaly Detection
• Novelty Detection Via Blurring
• Active learning using weakly supervised signals for quality inspection
• Synthetic training data generation for deep learning based quality inspection