A method for incremental semantic class discovery that builds a segmented 3D map from RGBD frames and identifies new classes from unlabeled coherent regions, achieving 10.7 Hz updates on NYUDv2.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Incremental Class Discovery for Semantic Segmentation with RGBD Sensing
A method for incremental semantic class discovery that builds a segmented 3D map from RGBD frames and identifies new classes from unlabeled coherent regions, achieving 10.7 Hz updates on NYUDv2.