COLA: COarse LAbel pre-training for 3D semantic segmentation of sparse LiDAR datasets.
Jules SanchezJean-Emmanuel DeschaudFrançois GoulettePublished in: ICRA (2023)
Keyphrases
- semantic segmentation
- pascal voc
- object detection
- bag of words
- label transfer
- object categories
- conditional random fields
- superpixels
- object classes
- object recognition
- object classification
- object segmentation
- training examples
- multi label
- training set
- high dimensional
- training samples
- class labels
- weakly supervised
- scene classification
- multiscale
- sparse representation
- labeled images
- image classification
- d objects
- information extraction
- image understanding
- higher order
- data sets
- generative model