NM-Hebb combines a Hebbian activation-weight alignment regulariser, a loss-gated neuromodulator, and a metric fine-tuning phase to improve CNN accuracy and embedding compactness.
Woo, et al., Convnext v2: Co-designing and scaling convnets with masked auto-encoders, in: CVPR, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
NM-Hebb: Coupling Local Hebbian Plasticity with Metric Learning for More Accurate and Interpretable CNNs
NM-Hebb combines a Hebbian activation-weight alignment regulariser, a loss-gated neuromodulator, and a metric fine-tuning phase to improve CNN accuracy and embedding compactness.