A dynamic graph message passing layer that learns input-dependent neighbor sampling, filter weights, and affinities improves scene understanding accuracy over fully-connected attention at a fraction of the FLOPs.
Gcnet: Non-local networks meet squeeze-excitation networks and beyond
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
-
Dynamic Graph Message Passing Networks
A dynamic graph message passing layer that learns input-dependent neighbor sampling, filter weights, and affinities improves scene understanding accuracy over fully-connected attention at a fraction of the FLOPs.