Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution Detection.
Yingwen WuRuiji YuXinwen ChengZhengbao HeXiaolin HuangPublished in: CoRR (2024)
Keyphrases
- neural network
- false positives
- network architecture
- detection algorithm
- automatic detection
- false alarms
- feature vectors
- object detection
- detection method
- data distribution
- adaboost classifier
- feature distributions
- human detection
- invariant features
- detection rate
- object recognition
- random variables
- face detection
- anomaly detection
- detection accuracy
- spatial distribution
- feature set
- probability distribution
- power law
- neural model
- input pattern
- image sequences