FGFP combines seven-parameter fractional Gaussian filters with adaptive unstructured pruning to compress CNNs by 69-97% with only about 1-2% accuracy loss.
Compact model training by low-rank projection with energy transfer
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FGFP: A Fractional Gaussian Filter and Pruning for Deep Neural Networks Compression
FGFP combines seven-parameter fractional Gaussian filters with adaptive unstructured pruning to compress CNNs by 69-97% with only about 1-2% accuracy loss.