Simultaneous or sequential integration of geometric-median filter pruning with 4-bit additive-power-of-two quantization compresses ResNet and VGG models on CIFAR-10 by about 15x with modest accuracy loss.
Thinet: A filter level pruni ng method for deep neural network compression,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Integrating Pruning with Quantization for Efficient Deep Neural Networks Compression
Simultaneous or sequential integration of geometric-median filter pruning with 4-bit additive-power-of-two quantization compresses ResNet and VGG models on CIFAR-10 by about 15x with modest accuracy loss.