Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Jack Barker 1 ; Neelanjan Bhowmik 2 ; Yona Falinie A. Gaus 1 and Toby Breckon 3 ; 1

Affiliations: 1 Department of Computer Science, Durham University, Durham, U.K ; 2 Department of Computer Science, Durham University, Durham, U.K. ; 3 Department of Engineering, Durham University, Durham, U.K.

Keyword(s): Novelty Detection, Denoising Autoencoder, Semi-supervised Anomaly Detection.

Abstract: Anomaly detection is the task of recognising novel samples which deviate significantly from pre-established normality. Abnormal classes are not present during training meaning that models must learn effective representations solely across normal class data samples. Deep Autoencoders (AE) have been widely used for anomaly detection tasks, but suffer from overfitting to a null identity function. To address this problem, we implement a training scheme applied to a Denoising Autoencoder (DAE) which introduces an efficient method of producing Adversarially Learned Continuous Noise (ALCN) to maximally globally corrupt the input prior to denoising. Prior methods have applied similar approaches of adversarial training to increase the robustness of DAE, however they exhibit limitations such as slow inference speed reducing their real-world applicability or producing generalised obfuscation which is more trivial to denoise. We show through rigorous evaluation that our ALCN method of regularisa tion during training improves AUC performance during inference while remaining efficient over both classical, leave-one-out novelty detection tasks with the variations-: 9 (normal) vs. 1 (abnormal) & 1 (normal) vs. 9 (abnormal); MNIST - AUCavg: 0.890 & 0.989, CIFAR-10 - AUCavg: 0.670 & 0.742, in addition to challenging real-world anomaly detection tasks: industrial inspection (MVTEC-AD AUCavg: 0.780) and plant disease detection (Plant Village - AUC: 0.770) when compared to prior approaches. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 70.40.220.129

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Barker, J. ; Bhowmik, N. ; A. Gaus, Y. and Breckon, T. (2023). Robust Semi-Supervised Anomaly Detection via Adversarially Learned Continuous Noise Corruption. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP; ISBN 978-989-758-634-7; ISSN 2184-4321, SciTePress, pages 615-625. DOI: 10.5220/0011684700003417

@conference{visapp23,
author={Jack Barker and Neelanjan Bhowmik and Yona Falinie {A. Gaus} and Toby Breckon},
title={Robust Semi-Supervised Anomaly Detection via Adversarially Learned Continuous Noise Corruption},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP},
year={2023},
pages={615-625},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011684700003417},
isbn={978-989-758-634-7},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP
TI - Robust Semi-Supervised Anomaly Detection via Adversarially Learned Continuous Noise Corruption
SN - 978-989-758-634-7
IS - 2184-4321
AU - Barker, J.
AU - Bhowmik, N.
AU - A. Gaus, Y.
AU - Breckon, T.
PY - 2023
SP - 615
EP - 625
DO - 10.5220/0011684700003417
PB - SciTePress