Conditioning Latent-Space Clusters for Real-World Anomaly Classification
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914635492360192 |
|---|---|
| author | Bogdoll, Daniel Pavlitska, Svetlana Klaus, Simon Zöllner, J. Marius |
| author_facet | Bogdoll, Daniel Pavlitska, Svetlana Klaus, Simon Zöllner, J. Marius |
| contents | Anomalies in the domain of autonomous driving are a major hindrance to the large-scale deployment of autonomous vehicles. In this work, we focus on high-resolution camera data from urban scenes that include anomalies of various types and sizes. Based on a Variational Autoencoder, we condition its latent space to classify samples as either normal data or anomalies. In order to emphasize especially small anomalies, we perform experiments where we provide the VAE with a discrepancy map as an additional input, evaluating its impact on the detection performance. Our method separates normal data and anomalies into isolated clusters while still reconstructing high-quality images, leading to meaningful latent representations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_09676 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Conditioning Latent-Space Clusters for Real-World Anomaly Classification Bogdoll, Daniel Pavlitska, Svetlana Klaus, Simon Zöllner, J. Marius Computer Vision and Pattern Recognition Artificial Intelligence Robotics Anomalies in the domain of autonomous driving are a major hindrance to the large-scale deployment of autonomous vehicles. In this work, we focus on high-resolution camera data from urban scenes that include anomalies of various types and sizes. Based on a Variational Autoencoder, we condition its latent space to classify samples as either normal data or anomalies. In order to emphasize especially small anomalies, we perform experiments where we provide the VAE with a discrepancy map as an additional input, evaluating its impact on the detection performance. Our method separates normal data and anomalies into isolated clusters while still reconstructing high-quality images, leading to meaningful latent representations. |
| title | Conditioning Latent-Space Clusters for Real-World Anomaly Classification |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Robotics |
| url | https://arxiv.org/abs/2309.09676 |