Papers › NeuralScale: Efficient Scaling of Neurons for Resource-Constrained Deep Neural Networks

NeuralScale: Efficient Scaling of Neurons for Resource-Constrained Deep Neural Networks

23 Jun 2020CVPR 2020 6arXiv:2006.12813archive 2025-07-28

Eugene Lee, Chen-Yi Lee

Deciding the amount of neurons during the design of a deep neural network to maximize performance is not intuitive. In this work, we attempt to search for the neuron (filter) configuration of a fixed network architecture that maximizes accuracy. Using iterative pruning methods as a proxy, we parameterize the change of the neuron (filter) number of each layer with respect to the change in parameters, allowing us to efficiently scale an architecture across arbitrary sizes. We also introduce architecture descent which iteratively refines the parameterized function used for model scaling. The combination of both proposed methods is coined as NeuralScale. To prove the efficiency of NeuralScale in terms of parameters, we show empirical simulations on VGG11, MobileNetV2 and ResNet18 using CIFAR10, CIFAR100 and TinyImageNet as benchmark datasets. Our results show an increase in accuracy of 3.04%, 8.56% and 3.41% for VGG11, MobileNetV2 and ResNet18 on CIFAR10, CIFAR100 and TinyImageNet respectively under a parameter-constrained setting (output neurons (filters) of default configuration with scaling factor of 0.25).

Paper PDF Conference PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

eugenelet/NeuralScale officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 Convolution Average Pooling Batch Normalization Bottleneck Residual Block Convolution Dense Connections Depthwise Convolution Depthwise Separable Convolution Dropout Global Average Pooling Inverted Residual Block Kaiming Initialization Max Pooling Pointwise Convolution Pruning ReLU Residual Block Residual Connection Softmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections