SegDA: Maximum Separable Segment Mask with Pseudo Labels for Domain Adaptive Semantic Segmentation.

Anant Khandelwal

Published in: ICCV (Workshops) (2023)

Keyphrases

semantic segmentation
street scenes
conditional random fields
superpixels
scene classification
weakly supervised
label transfer
object classes
object class
domain specific
object categories
bounding box
pascal voc
topic models
object segmentation
image classification
object detection