Fine-tuning convolutional neural network with transfer learning for semantic segmentation of ground-level oilseed rape images in a field with high weed pressure.
Alwaseela AbdallaHaiyan CenLiang WanReem RashidHaiyong WengWeijun ZhouYong HePublished in: Comput. Electron. Agric. (2019)
Keyphrases
- transfer learning
- fine tuning
- semantic segmentation
- pixel level
- image understanding
- input image
- convolutional neural network
- machine learning
- image collections
- test images
- image classification
- image features
- object recognition
- superpixels
- multiple images
- reinforcement learning
- image retrieval
- image annotation
- small number
- image set
- data sets
- bounding box
- collaborative filtering
- text classification
- active learning
- pairwise
- segmentation method
- machine learning algorithms
- labeled data
- feature extraction
- feature selection
- learning algorithm