Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 1,217

The DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index.

Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration

Open access
He, Yang, Liu, Ping, Wang, Ziwei, Hu, Zhilan, Yang, Yi·2019·2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Abstract

Previous works utilized “smaller-norm-less-important” criterion to prune filters with smaller norm values in a convolutional neural network. In this paper, we analyze this norm-based criterion and point out that its effectiveness depends on two requirements that are not always met: (1) the norm deviation of the filters should be large; (2) the minimum norm of the filters should be small. To solve this problem, we propose a novel filter pruning method, namely Filter Pruning via Geometric Median (FPGM), to compress the model regardless of those two requirements. Unlike previous methods, FPGM compresses CNN models by pruning filters with redundancy, rather than those with“relatively less” importance. When applied to two image classification benchmarks, our method validates its usefulness and strengths. Notably, on CIFAR-10, FPGM reduces more than 52% FLOPs on ResNet-110 with even 2.69% relative accuracy improvement. Moreover, on ILSVRC-2012, FPGM reduces more than 42% FLOPs on ResNet-101 without top-5 accuracy drop, which has advanced the state-of-the-art. Code is publicly available on GitHub: https://github.com/he-y/filter-pruning-geometric-median

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr.2019.00447

Cites

41 of 41 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 41 references

Research works printed but not linked: 7

  1. ye, 2018, Rethinking the smaller-norm-less-informative assumption in channel pruning of convolution layers, ICLRE
  2. han, 2015, Learning both weights and connections for efficient neural network, NIPS
  3. kim, 2018, Paraphrasing complex network: Network compression via factor transfer, NIPS
  4. dong, 2017, Learning to prune deep neural networks via layer-wise optimal brain surgeon, Advances in neural information processing systems, 4857
  5. guo, 2016, Dynamic network surgery for efficient DNNs, NIPS
  6. li, 2017, Pruning filters for efficient ConvNets, ICLRE
  7. zhou, 2017, Incremental network quantization: Towards lossless cnns with low- precision weights, ICLRE

Cited by

See all 1,217

Metadata

Authors
He, Y., Liu, P., Wang, Z., Hu, Z., & Yang, Y.
Venue
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2019-06
Pages
4335-4344
ISSN
1063-6919 (ISSN-L)
OpenAlex
W2928560789
Cited by
1,217
References
41
FWCI
53.81
Type
conference paper
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration. https://app.cochat.ai/papers/10.1109/cvpr.2019.00447
The paper
He, Y., Liu, P., Wang, Z., Hu, Z., & Yang, Y. (2019). Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr.2019.00447

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.