Taylor-expansion importance scoring enables layer-agnostic pruning of neural networks that outperforms prior methods on ImageNet accuracy-FLOPs trade-offs.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
dataset 2
citation-polarity summary
roles
dataset 2polarities
use dataset 2representative citing papers
DeepLabv3 improves semantic segmentation by capturing multi-scale context with cascaded or parallel atrous convolutions and adding global context to ASPP, achieving better results on PASCAL VOC 2012 without DenseCRF post-processing.
Linear learning-rate scaling plus warmup lets minibatch size 8192 train ResNet-50 on ImageNet in one hour at full small-batch accuracy.
citing papers explorer
-
Importance Estimation for Neural Network Pruning
Taylor-expansion importance scoring enables layer-agnostic pruning of neural networks that outperforms prior methods on ImageNet accuracy-FLOPs trade-offs.
-
Rethinking Atrous Convolution for Semantic Image Segmentation
DeepLabv3 improves semantic segmentation by capturing multi-scale context with cascaded or parallel atrous convolutions and adding global context to ASPP, achieving better results on PASCAL VOC 2012 without DenseCRF post-processing.
-
Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
Linear learning-rate scaling plus warmup lets minibatch size 8192 train ResNet-50 on ImageNet in one hour at full small-batch accuracy.