A semantic segmentation network that uses a learned shape mask to aggregate context from semantic-correlated regions, plus a labeling denoising module, reports state-of-the-art performance on six benchmarks.
Coco- stuff: Thing and stuff classes in context
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Semantic Correlation Promoted Shape-Variant Context for Segmentation
A semantic segmentation network that uses a learned shape mask to aggregate context from semantic-correlated regions, plus a labeling denoising module, reports state-of-the-art performance on six benchmarks.