DRÆM - A discriminatively trained reconstruction embedding for surface anomaly detection.
Vitjan ZavrtanikMatej KristanDanijel SkocajPublished in: CoRR (2021)
Keyphrases
- anomaly detection
- discriminatively trained
- three dimensional
- object detection
- intrusion detection
- detecting anomalies
- anomalous behavior
- sequence classification
- generative model
- network traffic
- discriminative learning
- network intrusion detection
- network anomaly detection
- detect anomalies
- negative selection algorithm
- intrusion detection system
- unsupervised learning
- pattern recognition
- data sets
- sequence data
- surface reconstruction
- high resolution
- support vector
- machine learning