ConSept: Continual Semantic Segmentation via Adapter-based Vision Transformer.

Bowen Dong Guanglei Yang Wangmeng Zuo Lei Zhang

Published in: CoRR (2024)

Keyphrases

semantic segmentation
street scenes
conditional random fields
superpixels
label transfer
weakly supervised
computer vision
object classes
object categories
scene classification
object class
image understanding
vision system
object detection
image processing
pascal voc
multiscale
image set
long range
topic models