EffiComm prunes BEV feature maps using a confidence mask and a graph-based adaptive keep-ratio policy, fuses survivors with Mixture-of-Experts attention, and reports 0.843 AP@0.7 on OPV2V while sending about 1.90 MB per frame.
Discograph: Learning distilled collaboration graph for multi-agent perception,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
EffiComm: Bandwidth Efficient Multi Agent Communication
EffiComm prunes BEV feature maps using a confidence mask and a graph-based adaptive keep-ratio policy, fuses survivors with Mixture-of-Experts attention, and reports 0.843 AP@0.7 on OPV2V while sending about 1.90 MB per frame.