Efficient Ladder-style DenseNets for Semantic Segmentation of Large Images.

Ivan Kreso Josip Krapac Sinisa Segvic

Published in: CoRR (2019)

Keyphrases

street scenes
semantic segmentation
input image
label transfer
image database
superpixels
image understanding
image data
object recognition
ground truth
image features
image set
test images
region of interest
image collections
pixel level
three dimensional
image classification
segmentation algorithm
generative model
small number
image retrieval
computer vision
conditional random fields
spatial information
segmentation method
image annotation
scene classification
multiscale