Boosting Multi-Modal Unsupervised Domain Adaptation for LiDAR Semantic Segmentation by Self-Supervised Depth Completion.
Adriano CardaceAndrea ContiPierluigi Zama RamirezRiccardo SpezialettiSamuele SaltiLuigi Di StefanoPublished in: IEEE Access (2023)
Keyphrases
- multi modal
- semantic segmentation
- conditional random fields
- superpixels
- weakly supervised
- scene classification
- object categories
- learning algorithm
- object classes
- image annotation
- depth map
- high resolution
- object detection
- high dimensional
- object class
- object segmentation
- pascal voc
- machine learning
- graphical models
- natural images
- higher order
- hidden markov models
- object recognition
- multiscale
- face recognition