LIX: Implicitly Infusing Spatial Geometric Prior Knowledge into Visual Semantic Segmentation for Autonomous Driving.
Sicen GuoZhiyuan WuQijun ChenIoannis PitasRui FanPublished in: CoRR (2024)
Keyphrases
- semantic segmentation
- autonomous driving
- prior knowledge
- grand challenge
- superpixels
- pascal voc
- conditional random fields
- scene classification
- weakly supervised
- object detection
- spatial relations
- object categories
- stereo vision
- spatial information
- generative model
- image processing
- natural scenes
- biologically inspired
- natural images
- higher order
- object recognition
- multiscale
- training data