Open Set Recognition Through Deep Neural Network Uncertainty: Does Out-of-Distribution Detection Require Generative Classifiers?
Martin MundtIuliia PliushchSagnik MajumderVisvanathan RameshPublished in: ICCV Workshops (2019)
Keyphrases
- neural network
- discriminative classifiers
- pattern recognition
- recognition rate
- scene text recognition
- road signs
- detection algorithm
- object detection
- traffic signs
- recognition accuracy
- partial occlusion
- unsupervised learning
- detection method
- support vector
- training data
- feature extraction
- decision trees
- generative model
- linear classifiers
- back propagation
- anomaly detection
- fuzzy logic
- knn
- artificial neural networks
- object recognition
- naive bayes
- random variables
- robust classification
- training set
- input pattern
- uncertain data
- handwritten digit recognition
- discriminative learning
- decision boundary
- nearest neighbour
- test set
- facial action units
- roc curve
- recognition algorithm
- neural network model
- radial basis function
- data distribution
- svm classifier
- data streams
- computer vision
- genetic algorithm