Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 164

The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.

Holistic CNN Compression via Low-Rank Decomposition with Knowledge Transfer

Lin, Shaohui, Ji, Rongrong, Chen, Chao, Tao, Dacheng, Luo, Jiebo·2019·IEEE Transactions on Pattern Analysis and Machine Intelligence

Abstract

Convolutional neural networks (CNNs) have achieved remarkable success in various computer vision tasks, which are extremely powerful to deal with massive training data by using tens of millions of parameters. However, CNNs often cost significant memory and computation consumption, which prohibits their usage in resource-limited environments such as mobile or embedded devices. To address the above issues, the existing approaches typically focus on either accelerating the convolutional layers or compressing the fully-connected layers separatedly, without pursuing a joint optimum. In this paper, we overcome such a limitation by introducing a holistic CNN compression framework, termed LRDKT, which works throughout both convolutional and fully-connected layers. First, a low-rank decomposition (LRD) scheme is proposed to remove redundancies across both convolutional kernels and fully-connected matrices, which has a novel closed-form solver to significantly improve the efficiency of the existing iterative optimization solvers. Second, a novel knowledge transfer (KT) based training scheme is introduced. To recover the accumulated accuracy loss and overcome the vanishing gradient, KT explicitly aligns outputs and intermediate responses from a teacher (original) network to its student (compressed) network. We have comprehensively analyzed and evaluated the compression and speedup ratios of the proposed model on MNIST and ILSVRC 2012 benchmarks. In both benchmarks, the proposed scheme has demonstrated superior performance gains over the state-of-the-art methods. We also demonstrate the proposed compression scheme for the task of transfer learning, including domain adaptation and object detection, which show exciting performance gains over the state-of-the-arts. Our source code and compressed models are available at https://github.com/ShaohuiLin/LRDKT.

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/tpami.2018.2873305

Cites

14 of 14 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 14 references

Cited by

See all 164

Metadata

Authors
Lin, S., Ji, R., Chen, C., Tao, D., & Luo, J.
Venue
IEEE Transactions on Pattern Analysis and Machine Intelligence
Published
2019-12-01
Volume
41
Issue
12
Pages
2889-2905
ISSN
  • 0162-8828 (ISSN-L)
  • 2160-9292
  • 1939-3539
OpenAlex
W2894994475
Cited by
164
References
14
FWCI
8.35
Type
journal article
Language
en
Open access
closed

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: Holistic CNN Compression via Low-Rank Decomposition with Knowledge Transfer. https://app.cochat.ai/papers/10.1109/tpami.2018.2873305
The paper
Lin, S., Ji, R., Chen, C., Tao, D., & Luo, J. (2019). Holistic CNN Compression via Low-Rank Decomposition with Knowledge Transfer. IEEE Transactions on Pattern Analysis and Machine Intelligence. https://doi.org/10.1109/tpami.2018.2873305

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.