MemFlow uses forward-only memorization via randomly connected neurons and spiking signals on a frozen backbone for unsupervised domain adaptation, claiming up to 10% gains at under 1% of traditional compute costs.
Unsupervised adaptation across domain shifts by generating intermediate data representations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MemFlow: A Lightweight Forward Memorizing Framework for Quick Domain Adaptive Feature Mapping
MemFlow uses forward-only memorization via randomly connected neurons and spiking signals on a frozen backbone for unsupervised domain adaptation, claiming up to 10% gains at under 1% of traditional compute costs.