A tiny-memory CNN generates part of its weights from a cellular automaton and uses multiplexer-based quantized residual links, reporting up to 1% higher accuracy than two compressed baselines at sub-2Mb sizes.
Residual attention network for image classification,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
MOGNET: A Mux-residual quantized Network leveraging Online-Generated weights
A tiny-memory CNN generates part of its weights from a cellular automaton and uses multiplexer-based quantized residual links, reporting up to 1% higher accuracy than two compressed baselines at sub-2Mb sizes.