Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 736

The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.

Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks With Octave Convolution

Open access
Chen, Yunpeng, Fan, Haoqi, Xu, Bing, Yan, Zhicheng, Kalantidis, Yannis, Rohrbach, Marcus, Shuicheng, Yan, Feng, Jiashi·2019·2019 IEEE/CVF International Conference on Computer Vision (ICCV)
DOI 10.1109/iccv.2019.00353
Open this paper in CoChat — free account

Abstract

In natural images, information is conveyed at different frequencies where higher frequencies are usually encoded with fine details and lower frequencies are usually encoded with global structures. Similarly, the output feature maps of a convolution layer can also be seen as a mixture of information at different frequencies. In this work, we propose to factorize the mixed feature maps by their frequencies, and design a novel Octave Convolution (OctConv) operation to store and process feature maps that vary spatially “slower” at a lower spatial resolution reducing both memory and computation cost. Unlike existing multi-scale methods, OctConv is formulated as a single, generic, plug-and-play convolutional unit that can be used as a direct replacement of (vanilla) convolutions without any adjustments in the network architecture. It is also orthogonal and complementary to methods that suggest better topologies or reduce channel-wise redundancy like group or depth-wise convolutions. We experimentally show that by simply replacing convolutions with OctConv, we can consistently boost accuracy for both image and video recognition tasks, while reducing memory and computational cost. An OctConv-equipped ResNet-152 can achieve 82.9% top-1 classification accuracy on ImageNet with merely 22.2 GFLOPs.

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/iccv.2019.00353

Cites

16 of 16 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 16 references

Research works printed but not linked: 37

  1. 10.1137/S0036141095289051 · DOI · Paper page
  2. sun, 2019, Deep high-resolution representation learning for human pose estimation, CVPR
  3. 10.1609/aaai.v33i01.33014780 · DOI · Paper page
  4. luo, 2018, Thinet: pruning cnn filters for a thinner net, IEEE Transactions on Pattern Analysis and Machine Intelligence
  5. stephane, 0, A Wavelet Tour of Signal Processing
  6. 10.1109/CVPR.2019.00497 · DOI
  7. simonyan, 2014, Very deep convo-lutional networks for large-scale image recognition, arXiv preprint arXiv 1409 1556
  8. 10.1109/CVPR.2018.00474 · DOI · Paper page
  9. lindeberg, 2013, Scale-Space Theory in Computer Vision, 256
  10. liu, 2018, Progressive neural architecture search, Proceedings of the European Conference on Com-puter Vsion (ECCV), 19
  11. carreira, 2018, A short note about kinetics-600, arXiv preprint arXiv 1808 02194
  12. 10.1113/jphysiol.1968.sp008574 · DOI · Paper page
  13. huang, 2018, Multi-scale dense networks for resource efficient image classification, ICLRE
  14. 10.1109/CVPR.2018.00291 · DOI · Paper page
  15. kay, 2017, The kinetics human action video dataset, arXiv preprint arXiv l 705 06950
  16. 2018, Math kernel library for deep neural net-works (mkldnn)
  17. 10.1109/CVPR.2017.433 · DOI
  18. 10.1109/CVPR.2017.660 · DOI · Paper page
  19. 10.1109/CVPR.2018.00907 · DOI · Paper page
  20. russell, 1988, Spatial vision, Oxford Psychology Series
  21. goyal, 2017, Accurate, large mini-batch sgd: Training imagenet in 1 hour, arXiv preprint arXiv l 706 02677
  22. guo, 2019, Gluoncv and gluonnlp: Deep learning in computer vision and natural language processing, arXiv preprint arXiv 1907 09977
  23. han, 2016, Dsd: Dense-sparse-dense training for deep neural networks, arXiv preprint arXiv 1607 04381
  24. howard, 2017, Mobilenets: Efficient convolutional neural networks for mobile vision applications, arXiv preprint arXiv 1 704 04861
  25. hu, 2018, Squeeze-and-excitation net-works, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 7132
  26. chen, 2019, Big-little net: An efficient multi-scale feature representation for visual and speech recognition, Proceed-ings of the Seventh International Conference on Learning Representations
  27. chen, 2018, Multi-fiber networks for video recog-nition, Proceedings of the European Conference on Com-puter Vsion (ECCV), 352
  28. chen, 2018, TVM: An automated end-to-end optimizing compiler for deep learning, 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18), 578
  29. chen, 2019, Graph-based global reasoning networks, Proc IEEE Con! Computer Vsion and Patter Recognition
  30. zhang, 2018, Shufflenet: An extremely efficient convolutional neural net-work for mobile devices, Proceedings of the IEEE Con-ference on Computer Vsion and Pattern Recognition, 6848
  31. chen, 2017, Dual path networks, Advances in neural information processing systems, 4467
  32. williams, 2008, Auto-tuning performance on mul-ticore computers
  33. zhang, 2018, mixup: Beyond empirical risk minimiza-tion, Proceedings of International Conference on Learning Representations
  34. 10.1109/CVPR.2017.634 · DOI · Paper page
  35. 10.1109/CVPR.2018.00821 · DOI · Paper page
  36. 10.1109/CVPR.2015.7298594 · DOI · Paper page
  37. wang, 2018, Elastic: Improving cnns with instance specific scaling policies, arXiv preprint arXiv 1812 02588

Cited by

See all 736

Metadata

Authors
Chen, Y., Fan, H., Xu, B., Yan, Z., Kalantidis, Y., Rohrbach, M., Shuicheng, Y., & Feng, J.
Venue
2019 IEEE/CVF International Conference on Computer Vision (ICCV)
Publisher
IEEE
Published
2019-10
Pages
3434-3443
DOI
10.1109/iccv.2019.00353
OpenAlex
W2988396473
Cited by
736
References
16
FWCI
30.36
Type
conference paper
Language
en
Open access
green
Licence

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: Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks With Octave Convolution. https://app.cochat.ai/papers/10.1109/iccv.2019.00353
The paper
Chen, Y., Fan, H., Xu, B., Yan, Z., Kalantidis, Y., Rohrbach, M., Shuicheng, Y., & Feng, J. (2019). Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks With Octave Convolution. 2019 IEEE/CVF International Conference on Computer Vision (ICCV). https://doi.org/10.1109/iccv.2019.00353

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.