A pivoted QR factorization based channel pruning technique achieves 4.29X and 2.84X FLOPs reduction on VGG-16 and ResNet-50 with about 1.4% top-5 accuracy loss on ImageNet.
Image captioning with semantic attention,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Efficient Inference of CNNs via Channel Pruning
A pivoted QR factorization based channel pruning technique achieves 4.29X and 2.84X FLOPs reduction on VGG-16 and ResNet-50 with about 1.4% top-5 accuracy loss on ImageNet.