Loading...
Please wait, while we are loading the content...
Similar Documents
Latent-Insensitive Autoencoders for Anomaly Detection
| Content Provider | MDPI |
|---|---|
| Author | Battikh, Muhammad S. Lenskiy, Artem A. |
| Copyright Year | 2021 |
| Description | Reconstruction-based approaches to anomaly detection tend to fall short when applied to complex datasets with target classes that possess high inter-class variance. Similar to the idea of self-taught learning used in transfer learning, many domains are rich with similar unlabeled datasets that could be leveraged as a proxy for out-of-distribution samples. In this paper we introduce the latent-insensitive autoencoder (LIS-AE) where unlabeled data from a similar domain are utilized as negative examples to shape the latent layer (bottleneck) of a regular autoencoder such that it is only capable of reconstructing one task. We provide theoretical justification for the proposed training process and loss functions along with an extensive ablation study highlighting important aspects of our model. We test our model in multiple anomaly detection settings presenting quantitative and qualitative analysis showcasing the significant performance improvement of our model for anomaly detection tasks. |
| Starting Page | 112 |
| e-ISSN | 22277390 |
| DOI | 10.3390/math10010112 |
| Journal | Mathematics |
| Issue Number | 1 |
| Volume Number | 10 |
| Language | English |
| Publisher | MDPI |
| Publisher Date | 2021-12-30 |
| Access Restriction | Open |
| Subject Keyword | Mathematics Industrial Engineering Anomaly Detection Autoencoders One-class Classification Principal Components Analysis Self-taught Learning Negative Examples |
| Content Type | Text |
| Resource Type | Article |
