Accurate Parts Visualization for Explaining CNN Reasoning via Semantic Segmentation.

Ren Harada Antonio Tejero-de-Pablos Tatsuya Harada

Published in: BMVC (2020)

Keyphrases

semantic segmentation
street scenes
object classes
superpixels
conditional random fields
scene classification
weakly supervised
label transfer
object class
object categories
feature extraction
image processing
d objects
multiscale
spatial relations
visual words
training set
object recognition
computer vision