Utilizing Google Images for Training Classifiers in CRF-Based Semantic Segmentation.
Rizki Perdana RangkutiVektor Dewanto AprinaldiWisnu JatmikoPublished in: J. Adv. Comput. Intell. Intell. Informatics (2016)
Keyphrases
- semantic segmentation
- street scenes
- conditional random fields
- label transfer
- image set
- superpixels
- object categories
- labeled images
- image database
- image understanding
- segmentation method
- ground truth
- training set
- input image
- image classification
- weakly supervised
- image features
- multiple images
- object classes
- test images
- pascal voc
- training samples
- object recognition
- decision trees
- object class
- pixel level
- scene classification
- object detection
- training data
- image annotation
- keypoints
- training examples
- graphical models