HMDMV trains a multi-view classifier on all view subsets with uncertainty-weighted fusion and hierarchical mutual distillation, improving accuracy and supporting flexible view counts at inference.
Learning efficient object detection mod- els with knowledge distillation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hierarchical mutual distillation for multi-view fusion: Learning from all possible view combinations
HMDMV trains a multi-view classifier on all view subsets with uncertainty-weighted fusion and hierarchical mutual distillation, improving accuracy and supporting flexible view counts at inference.