Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

End-to-End Convolutional Activation Anomaly Analysis for Anomaly Detection

Aleksander Kozłowski, Daniel Ponikowski, Piotr Żukiewicz, Paweł Twardowski

Abstract

We propose an End-to-end Convolutional Activation Anomaly Analysis (E2E-CA$^3$), which is a significant extension of A$^3$ anomaly detection approach proposed by Sperl, Schulze and Böttinger, both in terms of architecture and scope of application. In contrast to the original idea, we utilize a convolutional autoencoder as a target network, which allows for natural application of the method both to image and tabular data. The alarm network is also designed as a CNN, where the activations of convolutional layers from CAE are stacked together into $k+1-$dimensional tensor. Moreover, we combine the classification loss of the alarm network with the reconstruction error of the target CAE, as a "best of both worlds" approach, which greatly increases the versatility of the network. The evaluation shows that despite generally straightforward and lightweight architecture, it has a very promising anomaly detection performance on common datasets such as MNIST, CIFAR-10 and KDDcup99.

End-to-End Convolutional Activation Anomaly Analysis for Anomaly Detection

Abstract

We propose an End-to-end Convolutional Activation Anomaly Analysis (E2E-CA), which is a significant extension of A anomaly detection approach proposed by Sperl, Schulze and Böttinger, both in terms of architecture and scope of application. In contrast to the original idea, we utilize a convolutional autoencoder as a target network, which allows for natural application of the method both to image and tabular data. The alarm network is also designed as a CNN, where the activations of convolutional layers from CAE are stacked together into dimensional tensor. Moreover, we combine the classification loss of the alarm network with the reconstruction error of the target CAE, as a "best of both worlds" approach, which greatly increases the versatility of the network. The evaluation shows that despite generally straightforward and lightweight architecture, it has a very promising anomaly detection performance on common datasets such as MNIST, CIFAR-10 and KDDcup99.

Paper Structure

This paper contains 16 sections, 2 equations, 1 figure, 2 tables.

Table of Contents

  1. Introduction
  2. Related work
  3. Methodology
  4. Architecture
  5. Convolutional layers
  6. Image data
  7. Tabular data
  8. End-to-end learning
  9. Experiments
  10. Setup
  11. Image datasets
  12. Tabular datasets
  13. Results
  14. Image datasets
  15. Tabular datasets
  16. ...and 1 more sections

Figures (1)

  • Figure 1: Architecture diagram