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

By Marco Rudolph, Bastian Wandt, Bodo Rosenhahn. IEEE Workshop/Winter Conference on Applications of Computer Vision, 2020

442 citations recorded by the source corpus.

The detection of manufacturing errors is crucial in fabrication processes to ensure product quality and safety standards. Since many defects occur very rarely and their characteristics are mostly unknown a priori, their detection is still an open research question. To this end, we propose DifferNet: It leverages the descriptiveness of features extracted by convolutional neural networks to estimate their density using normalizing flows. Normalizing flows are well-suited to deal with low dimensional data distributions. However, they struggle with the high dimensionality of images. Therefore, we employ a multi-scale feature extractor which enables the normalizing flow to assign meaningful likelihoods to the images. Based on these likelihoods we develop a scoring function that indicates defects. Moreover, propagating the score back to the image enables pixel-wise localization. To achieve a high robustness and performance we exploit multiple transformations in training and evaluation. In contrast to most other methods, ours does not require a large number of training samples and performs well with as low as 16 images. We demonstrate the superior performance over existing approaches on the challenging and newly proposed MVTec AD [4] and Magnetic Tile Defects [14] datasets.

Subfields: Electrical and Electronic Engineering, Industrial and Manufacturing Engineering, Mechanical Engineering

View Paper: https://www.semanticscholar.org/paper/b1464ca857593c049873421db2f37bf2d0ff676d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Electrical and Electronic Engineering

In Industrial and Manufacturing Engineering

In Mechanical Engineering

Citations in the corpus

SimpleNet: A Simple Network for Image Anomaly Detection and Localization (2023, unknown): “CS-Flow [24], CFLOW-AD [12], and DifferNet [23] propose to transform the normal feature distribution into Gaussian distribution via normalizing flow (NF) [20].”
WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation (2023, background): “Recent works [32, 39] explored few-shot setups by leveraging augmentation to expand the small support set for better normality modeling.”
Towards Total Recall in Industrial Anomaly Detection (2021, methodology): “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].”
EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies (2023, methodology): “Common methods include multivariate Gaussian distributions [16, 30, 48], Gaussian Mixture Models [38, 72], Normalizing Flows [22,47,51,52,68], and the k-Nearest Neighbor (kNN) algorithm [14, 39, 40, 50].”
CutPaste: Self-Supervised Learning for Anomaly Detection and Localization (2021, methodology): “We note that some of these methods use ImageNet pretrained model for transfer learning, either by fine-tuning (DOCC) or distillation (uninformed student).”
FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows (2021, methodology): “Recently, some works (Rudolph, Wandt, and Rosenhahn 2021; Gudovskiy, Ishizaka, and Kozuka 2021) began to use normalizing ﬂow (Kingma and Dhariwal 2018) to estimate distribution.”
CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows (2021, methodology): “DifferNet [30] uses a promising class of generative models called normalizing flows (NFLOWs) [9] for image-level AD.”