A dynamic neuron replacement scheme, with gradients reweighted by class frequency, improves long-tailed image classification accuracy by 1-4% over fixed networks in the reported experiments.
Provable benefits of overparameterization in model compression: From double descent to pruning neural networks
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
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Long-Tailed Data Classification by Increasing and Decreasing Neurons During Training
A dynamic neuron replacement scheme, with gradients reweighted by class frequency, improves long-tailed image classification accuracy by 1-4% over fixed networks in the reported experiments.