A Re-Parameterized Vision Transformer (ReVT) for Domain-Generalized Semantic Segmentation.

Jan-Aike Termöhlen Timo Bartels Tim Fingscheidt

Published in: ICCV (Workshops) (2023)

Keyphrases

semantic segmentation
street scenes
label transfer
computer vision
vision system
conditional random fields
weakly supervised
scene classification
domain specific
superpixels
object recognition
hidden markov models
text mining
n gram
object categories
object classes