CoChat

Interleaved Structured Sparse Convolutional Neural Networks

Open access
Xie, Guotian, Wang, Jingdong, Zhang, Ting, Lai, Jianhuang, Hong, Richang, Qi, Guo-Jun · 2018 · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Cited by 130

The DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.

Abstract

In this paper, we study the problem of designing efficient convolutional neural network architectures with the interest in eliminating the redundancy in convolution kernels. In addition to structured sparse kernels, low-rank kernels and the product of low-rank kernels, the product of structured sparse kernels, which is a framework for interpreting the recently-developed interleaved group convolutions (IGC) and its variants (e.g., Xception), has been attracting increasing interests. Motivated by the observation that the convolutions contained in a group convolution in IGC can be further decomposed in the same manner, we present a modularized building block, IGC-V2: interleaved structured sparse convolutions. It generalizes interleaved group convolutions, which is composed of two structured sparse kernels, to the product of more structured sparse kernels, further eliminating the redundancy. We present the complementary condition and the balance condition to guide the design of structured sparse kernels, obtaining a balance among three aspects: model size, computation complexity and classification accuracy. Experimental results demonstrate the advantage on the balance among these three aspects compared to interleaved group convolutions and Xception, and competitive performance compared to other state-of-the-art architecture design methods.

Overview

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

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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

Integrity signals

Registry

Crossref · 10.1109/cvpr.2018.00922

Cites

18 of 18 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.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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 18 references

Research works printed but not linked: 32

  1. wen, 2016, Learning structured sparsity in deep neural networks, NIPS, 2074
  2. wang, 2016, Deeply-fused nets
  3. singh, 2016, Swapout: Learning an ensemble of deep architectures, NIPS, 28
  4. 10.1007/s11263-015-0816-y · DOI · Paper page
  5. rastegari, 2016, Xnornet: Imagenet classification using binary convolutional neural networks, ECCV, 525
  6. 10.1109/TPAMI.2008.128 · DOI · Paper page
  7. targ, 2016, Resnet in resnet Generalizing residual architectures
  8. srivastava, 2015, Training very deep networks, NIPS, 2377
  9. 10.1109/ICCV.2017.78 · DOI · Paper page
  10. ioannou, 2015, Training cnns with low-rank filters for efficient image classification
  11. jia, 2014, Caffe Convolutional Architecture for Fast Feature Embedding
  12. kim, 2015, Compression of deep convolutional neural networks for fast and low power mobile applications
  13. krizhevsky, 2009, Learning multiple layers of features from tiny images
  14. larsson, 2016, Fractalnet Ultra-deep neural networks without residuals
  15. lee, 2015, Deeply-supervised nets, AISTATS
  16. lee, 2013, Local low-rank matrix approximation, ICML (2), 82
  17. mamalet, 2012, Simplifying convnets for fast learning, ICANN, 58
  18. courbariaux, 2016, Binarized neural networks Training deep neural networks with weights and activations constrained to +1 or ?1
  19. park, 2016, Faster cnns with direct sparse convolutions and guided pruning
  20. han, 2015, Deep compression Compressing deep neural network with pruning trained quantization and huffman coding
  21. huang, 2017, Snapshot ensembles Train 1 get M for free
  22. cordeiro, 0, Wide residual network for the tiny imagenet challenge
  23. huang, 2016, Densely Connected Convolutional Networks
  24. lee, 2016, L-LORMA: local low-rank matrix approximation, Journal of Machine Learning Research, 17, 15:1
  25. zhou, 2017, Incremental network quantization Towards lossless cnns with low-precision weights
  26. zhu, 2016, Trained ternary quantization
  27. liu, 2015, Sparse convolutional neural networks, CVPR, 806
  28. xie, 2016, Aggregated residual transformations for deep neural networks
  29. lin, 2013, Network in Network
  30. zhao, 2016, Deep convolutional neural networks with merge-and-run mappings
  31. 10.1109/ICCV.2017.541 · DOI · Paper page
  32. zhang, 2017, Interleaved group convolutions for deep neural networks

Cited by

See all 130

Metadata

Authors
Xie, G., Wang, J., Zhang, T., Lai, J., Hong, R., & Qi, G.-J.
Venue
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Publisher
IEEE
Published
2018-06
Pages
8847-8856
ISSN
1063-6919 (ISSN-L)
OpenAlex
W2963216524
Cited by
130
References
18
FWCI
6.85
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: Interleaved Structured Sparse Convolutional Neural Networks. https://app.cochat.ai/papers/10.1109/cvpr.2018.00922
The paper
Xie, G., Wang, J., Zhang, T., Lai, J., Hong, R., & Qi, G.-J. (2018). Interleaved Structured Sparse Convolutional Neural Networks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. https://doi.org/10.1109/cvpr.2018.00922

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.