Papers › Quantisation and Pruning for Neural Network Compression and Regularisation

Quantisation and Pruning for Neural Network Compression and Regularisation

14 Jan 2020arXiv:2001.04850archive 2025-07-28

Kimessha Paupamah, Steven James, Richard Klein

Deep neural networks are typically too computationally expensive to run in real-time on consumer-grade hardware and low-powered devices. In this paper, we investigate reducing the computational and memory requirements of neural networks through network pruning and quantisation. We examine their efficacy on large networks like AlexNet compared to recent compact architectures: ShuffleNet and MobileNet. Our results show that pruning and quantisation compresses these networks to less than half their original size and improves their efficiency, particularly on MobileNet with a 7x speedup. We also demonstrate that pruning, in addition to reducing the number of parameters in a network, can aid in the correction of overfitting.

PaperPDFCode

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

Code

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.

Tasks

Network PruningNeural Network Compression

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Network Pruning CIFAR-10 MobileNet – Quantised Inference Time (ms) 4.74 #2 of 4 Archive leaderboard report
Network Pruning CIFAR-10 AlexNet – Quantised Inference Time (ms) 5.23 #3 of 4 Archive leaderboard report
Network Pruning CIFAR-10 ShuffleNet – Quantised Inference Time (ms) 23.15 #4 of 4 Archive leaderboard report
Neural Network Compression CIFAR-10 ShuffleNet – Quantised Size (MB) 1.9 #1 of 5 Archive leaderboard report
Neural Network Compression CIFAR-10 MobileNet – Quantised Size (MB) 2.9 #2 of 5 Archive leaderboard report
Neural Network Compression CIFAR-10 AlexNet – Quantised Size (MB) 54.6 #3 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationChannel ShuffleConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDropoutGlobal Average PoolingGrouped ConvolutionGroupwise Point ConvolutionLocal Response NormalizationMax PoolingMobileNetV1Pointwise ConvolutionPruningReLUResidual ConnectionShuffleNetShuffleNet BlockSoftmax

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