Linear learning-rate scaling plus warmup lets minibatch size 8192 train ResNet-50 on ImageNet in one hour at full small-batch accuracy.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2roles
background 1polarities
background 1representative citing papers
Growing CNN capacity by widening or deepening layers with normalized new units outperforms standard fine-tuning on vision benchmarks.
citing papers explorer
-
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.
-
Growing a Brain: Fine-Tuning by Increasing Model Capacity
Growing CNN capacity by widening or deepening layers with normalized new units outperforms standard fine-tuning on vision benchmarks.