Deep Unsupervised Image Anomaly Detection: An Information Theoretic Framework

12/09/2020
by   Fei Ye, et al.
0

Surrogate task based methods have recently shown great promise for unsupervised image anomaly detection. However, there is no guarantee that the surrogate tasks share the consistent optimization direction with anomaly detection. In this paper, we return to a direct objective function for anomaly detection with information theory, which maximizes the distance between normal and anomalous data in terms of the joint distribution of images and their representation. Unfortunately, this objective function is not directly optimizable under the unsupervised setting where no anomalous data is provided during training. Through mathematical analysis of the above objective function, we manage to decompose it into four components. In order to optimize in an unsupervised fashion, we show that, under the assumption that distribution of the normal and anomalous data are separable in the latent space, its lower bound can be considered as a function which weights the trade-off between mutual information and entropy. This objective function is able to explain why the surrogate task based methods are effective for anomaly detection and further point out the potential direction of improvement. Based on this object function we introduce a novel information theoretic framework for unsupervised image anomaly detection. Extensive experiments have demonstrated that the proposed framework significantly outperforms several state-of-the-arts on multiple benchmark data sets.

READ FULL TEXT

page 1

page 7

page 9

research
12/09/2020

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

This paper explores semi-supervised anomaly detection, a more practical ...
research
11/25/2019

Inverse-Transform AutoEncoder for Anomaly Detection

Reconstruction-based methods have recently shown great promise for anoma...
research
05/30/2019

Information theoretic learning of robust deep representations

We propose a novel objective function for learning robust deep represent...
research
12/21/2021

Anomaly Clustering: Grouping Images into Coherent Clusters of Anomaly Types

We introduce anomaly clustering, whose goal is to group data into semant...
research
10/06/2021

Anomaly Detection based on Compressed Data: an Information Theoretic Characterization

We analyze the effect of lossy compression in the processing of sensor s...
research
08/02/2019

TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems

A trojan backdoor is a hidden pattern typically implanted in a deep neur...
research
11/25/2021

Few-shot Deep Representation Learning based on Information Bottleneck Principle

In a standard anomaly detection problem, a detection model is trained in...

Please sign up or login with your details

Forgot password? Click here to reset