ZERO - Detect objects without training examples by knowing their parts.
Gertjan J. BurghoutsFieke HillerströmPublished in: AAAI Spring Symposium: Combining Machine Learning with Knowledge Engineering (2021)
Keyphrases
- training examples
- object categories
- object classes
- small number
- training set
- active learning
- training data
- supervised learning
- learning algorithm
- training phase
- domain theory
- support vector
- labeled examples
- object segmentation
- spatial relations
- d objects
- prior domain knowledge
- object class
- labeled data
- class labels
- training samples
- positive examples
- unlabeled data
- object detection
- decision trees
- information retrieval
- class distribution
- domain specific
- target concept
- negative examples