Y-GAN
learning dual data representations for anomaly detection in images
Abstract
We propose a novel reconstruction-based model for anomaly detection in image data, called ’Y-GAN’. The model consists of a Y-shaped auto-encoder and represents images in two separate latent spaces. The first captures meaningful image semantics, which are key for representing (normal) training data, whereas the second encodes low-level residual image characteristics. To ensure the dual representations encode mutually exclusive information, a disentanglement procedure is designed around a latent (proxy) classifier. Additionally, a novel representation-consistency mechanism is proposed to prevent information leakage between the latent spaces. The model is trained in a one-class learning setting using only normal training data. Due to the separation of semantically-relevant and residual information, Y-GAN is able to derive informative data representations that allow for efficacious anomaly detection across a diverse set of anomaly detection tasks. The model is evaluated in comprehensive experiments with several recent anomaly detection models using four popular image datasets, i.e., MNIST, FMNIST, CIFAR10, and PlantVillage. Experimental results show that Y-GAN outperforms all tested models by a considerable margin and yields state-of-the-art results. The source code for the model is made publicly available at https://github.com/MIvanovska/Y-GAN.
Keywords
detekcija anomalij;enorazredno učenje;globoko učenje;anomaly detection;pone-class learning;deeplearning;
Data
| Language: | English |
|---|---|
| Year of publishing: | 2024 |
| Typology: | 1.01 - Original Scientific Article |
| Organization: | UL FE - Faculty of Electrical Engineering |
| UDC: | 004.93 |
| COBISS: |
184821507
|
| ISSN: | 1873-6793 |
| Views: | 80 |
| Downloads: | 33 |
| Average score: | 0 (0 votes) |
| Metadata: |
|
Other data
| Secondary language: | Slovenian |
|---|---|
| Secondary keywords: | detekcija anomalij;enorazredno učenje;globoko učenje; |
| Type (COBISS): | Article |
| Pages: | 17 str. |
| Issue: | ǂVol. ǂ248, [article no.] 123410 |
| Chronology: | 15 Avg. 2024 |
| DOI: | 10.1016/j.eswa.2024.123410 |
| ID: | 23628106 |
Recommended works:
Y-GAN
2024,
learning dual data representations for anomaly detection in images
Mixed supervision for surface-defect detection
2022,
master's thesis
Podatkovna zbirka redkih realističnih slikovnih anomalij za testiranje generativnih globokih nevronskih mrež
2020,
no subtitle data available
Detecting surface anomalies with deep learning
2022,
no subtitle data available
Analiza merilnih podatkov mobilnega omrežja
2019,
no subtitle data available