DRÆM – A discriminatively trained reconstruction embedding for surface anomaly detection

By Vitjan Zavrtanik, Matej Kristan, Danijel Skocaj. IEEE International Conference on Computer Vision, 2021

1,151 citations recorded by the source corpus.

Visual surface anomaly detection aims to detect local image regions that significantly deviate from normal appearance. Recent surface anomaly detection methods rely on generative models to accurately reconstruct the normal areas and to fail on anomalies. These methods are trained only on anomaly-free images, and often require hand-crafted post-processing steps to localize the anomalies, which prohibits optimizing the feature extraction for maximal detection capability. In addition to reconstructive approach, we cast surface anomaly detection primarily as a discriminative problem and propose a discriminatively trained reconstruction anomaly embedding model (DRÆM). The proposed method learns a joint representation of an anomalous image and its anomaly-free reconstruction, while simultaneously learning a decision boundary between normal and anomalous examples. The method enables direct anomaly localization without the need for additional complicated post-processing of the network output and can be trained using simple and general anomaly simulations. On the challenging MVTec anomaly detection dataset, DRÆM outperforms the current state-of-the-art unsupervised methods by a large margin and even de-livers detection performance close to the fully-supervised methods on the widely used DAGM surface-defect detection dataset, while substantially outperforming them in localization accuracy. Code at github.com/VitjanZ/DRAEM.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Industrial and Manufacturing Engineering

View Paper: https://www.semanticscholar.org/paper/95a26eafabf06b1fc5dec6c460a927cf5964e97e

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Industrial and Manufacturing Engineering

Citations in the corpus

SimpleNet: A Simple Network for Image Anomaly Detection and Localization (2023, methodology): “The synthesizing-based methods [17, 30] estimate the decision boundary between the normal and anomalous by training on synthetic anomalies generated on anomaly-free images.”
Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection (2021, methodology): “For the methods [18,34,37,39,49,79] chosen to serve as underlying models for SSPCAB, we use the official code from the repositories provided by the corresponding authors, inheriting the hyperparameters, e.”
A Unified Model for Multi-class Anomaly Detection (2022, background): “US [3] PSVDD [15] PaDiM [5] CutPaste [10] FCDD [11] MKD [12] DRAEM [16] Ours FLOPs(G) 60.”
OpenOOD: Benchmarking Generalized Out-of-Distribution Detection (2022, methodology): “DRÆM [58] is a reconstruction-based method that feeds the given image and its reconstructed version into a discriminative network to produce anomaly scores.”
WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation (2023, background): “Due to the scarcity of anomalies, the major focus has been on oneclass methods with many normal images [7, 8, 20, 49, 51, 53].”
Deep Industrial Image Anomaly Detection: A Survey (2023, methodology): “The paper generates abnormal samples in feature level and perform better than DRAEM.”
DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detection (2022, methodology): “Another strategy proposed in [37] and also adopted in [38] used two-dimensional Perlin noise to simulate a more realistic anomalous image.”
Revisiting Reverse Distillation for Anomaly Detection (2023, methodology): “Later methods use deep models to improve the quality of reconstructed images [41, 42].”