Automatic labeling to overcome the limitations of deep learning in applications with insufficient training data: A case study on fruit detection in pear orchards.
Maria CulmanStephanie DelalieuxBart BeusenBen SomersPublished in: Comput. Electron. Agric. (2023)
Keyphrases
- text mining
- deep learning
- training data
- machine learning
- unsupervised learning
- unsupervised feature learning
- supervised learning
- decision trees
- data sets
- object detection
- weakly supervised
- deep architectures
- active learning
- topic models
- mental models
- learning algorithm
- prior knowledge
- training examples
- decision makers
- maximum likelihood