Conditioning Latent-Space Clusters for Real-World Anomaly Classification
This addresses the challenge of anomaly detection in autonomous vehicles, which is crucial for safe deployment, but the approach appears incremental as it builds on existing VAE methods with added conditioning and discrepancy maps.
The paper tackles the problem of detecting anomalies in high-resolution urban camera data for autonomous driving by conditioning a Variational Autoencoder's latent space to classify samples as normal or anomalous, achieving separation into isolated clusters while maintaining high-quality image reconstruction.
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.