Inverse-Transform AutoEncoder for Anomaly Detection

11/25/2019
by   Chaoqing Huang, et al.
46

Reconstruction-based methods have recently shown great promise for anomaly detection. We here propose a new transform-based framework for anomaly detection. A selected set of transformations based on human priors is used to erase certain targeted information from input data. An inverse-transform autoencoder is trained with the normal data only to embed corresponding erased information during the restoration of the original data. The normal and anomalous data are thus expected to be differentiable based on restoration errors. Extensive experiments have demonstrated that the proposed method significantly outperforms several state-of-the-arts on multiple benchmark datasets, especially on ImageNet, increasing the AUROC of the top-performing baseline by 10.1 detection dataset MVTec AD and a video anomaly detection dataset ShanghaiTech to validate the effectiveness of the method in real-world environments.

READ FULL TEXT

page 8

page 13

research
12/09/2020

Deep Unsupervised Image Anomaly Detection: An Information Theoretic Framework

Surrogate task based methods have recently shown great promise for unsup...
research
12/09/2020

ESAD: End-to-end Deep Semi-supervised Anomaly Detection

This paper explores semi-supervised anomaly detection, a more practical ...
research
03/22/2021

Unsupervised Two-Stage Anomaly Detection

Anomaly detection from a single image is challenging since anomaly data ...
research
07/06/2023

Noise-to-Norm Reconstruction for Industrial Anomaly Detection and Localization

Anomaly detection has a wide range of applications and is especially imp...
research
08/16/2017

Limiting the Reconstruction Capability of Generative Neural Network using Negative Learning

Generative models are widely used for unsupervised learning with various...
research
03/23/2023

Hierarchical Semantic Contrast for Scene-aware Video Anomaly Detection

Increasing scene-awareness is a key challenge in video anomaly detection...

Please sign up or login with your details

Forgot password? Click here to reset