Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detection.
Thang DoanXin LiSima BehpourWenbin HeLiang GouLiu RenPublished in: AAAI (2024)
Keyphrases
- structure learning
- open world
- bayesian networks
- graphical models
- closed world
- incomplete information
- conditional independence
- parameter estimation
- transfer learning
- sample size
- network structure
- markov networks
- data exchange
- probability distribution
- distance function
- query answering
- maximum likelihood estimation
- random variables
- data sets
- maximum likelihood
- least squares
- information extraction
- knowledge base
- feature selection
- machine learning