Patchwise Sparse Dictionary Learning from pre-trained Neural Network Activation Maps for Anomaly Detection in Images.
Stefano SameleMatteo MatteucciPublished in: ICPR (2022)
Keyphrases
- anomaly detection
- dictionary learning
- sparse representation
- sparse coding
- intrusion detection
- image classification
- test images
- input image
- image features
- object recognition
- unsupervised learning
- intrusion detection system
- image retrieval
- detect anomalies
- pattern recognition
- image representation
- bag of words
- neural network
- trained neural network
- input data
- higher order
- artificial neural networks
- high dimensional
- association rules
- training data
- data mining
- data sets