A structural pruning method combining channel-attention importance scores with a hard-example-focused fine-tuning loss reportedly achieves state-of-the-art pruned accuracy on EuroSAT and UCMerced.
Pruning convolutional neural networks with an attention mechanism for remote sensing image classi- fication,
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.CV 1years
2024 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
RemoteTrimmer: Adaptive Structural Pruning for Remote Sensing Image Classification
A structural pruning method combining channel-attention importance scores with a hard-example-focused fine-tuning loss reportedly achieves state-of-the-art pruned accuracy on EuroSAT and UCMerced.