SeAl-KD improves SNN accuracy by equalizing competing logits at erroneous timesteps and reweighting temporal alignment using confidence and inter-timestep similarity.
Learning both weights and connections for efficient neural network.Advances in neural information processing systems, 28,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Not All Timesteps Matter Equally: Selective Alignment Knowledge Distillation for Spiking Neural Networks
SeAl-KD improves SNN accuracy by equalizing competing logits at erroneous timesteps and reweighting temporal alignment using confidence and inter-timestep similarity.