What Does Really Count? Estimating Relevance of Corner Cases for Semantic Segmentation in Automated Driving.
Jasmin BreitensteinFlorian HeideckerMaria LyssenkoDaniel BogdollMaarten BieshaarJ. Marius ZöllnerBernhard SickTim FingscheidtPublished in: ICCV (Workshops) (2023)
Keyphrases
- semantic segmentation
- street scenes
- superpixels
- weakly supervised
- label transfer
- conditional random fields
- object class
- scene classification
- object categories
- object detection
- pascal voc
- information retrieval
- image understanding
- multiple images
- graphical models
- higher order
- feature vectors
- viewpoint
- object recognition
- multiscale
- training data
- learning algorithm