Conference paper · 2022 · Open access
Kernel Modulation: A Parameter-Efficient Method for Training Convolutional Neural Networks
Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition, 2192–2198 · Published 21 August 2022 · DOI 10.1109/icpr56361.2022.9956386
In brief
“Kernel Modulation: A Parameter-Efficient Method for Training Convolutional Neural Networks” is a 2022 conference paper by Yuhuang Hu and Shih‐Chii Liu, published in Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition. OpenAlex counts 1 citations as of 18 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 1
- Most cited in
- 2025 (1)
- Field-weighted impact
- 0.07
- References
- 33
- Authors
- 2
Abstract
Deep Neural Networks, particularly Convolutional Neural Networks (ConvNets), have achieved incredible success in many vision tasks, but they usually require millions of parameters for good accuracy performance. With increasing applications that use ConvNets, updating hundreds of networks for multiple tasks on an embedded device can be costly in terms of memory, bandwidth, and energy. Approaches to reduce this cost include model compression and parameter-efficient models that adapt a subset of network layers for each new task. This work proposes a novel parameter-efficient kernel modulation (KM) method that adapts all parameters of a base network instead of a subset of layers. KM uses lightweight task-specialized kernel modulators that require only an additional 1.4% of the base network parameters. With multiple tasks, only the task-specialized KM weights are communicated and stored on the end-user device. We applied this method in training ConvNets for Transfer Learning and Meta-Learning scenarios. Our results show that KM delivers up to 9% higher accuracy compared to other parameter-efficient methods on the Transfer Learning benchmark.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Hu, Y., & Liu, S. (2022). Kernel Modulation: A Parameter-Efficient Method for Training Convolutional Neural Networks. Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition, 2192–2198. https://doi.org/10.1109/icpr56361.2022.9956386
MLA 9
Hu, Yuhuang, and Shih‐Chii Liu. “Kernel Modulation: A Parameter-Efficient Method for Training Convolutional Neural Networks.” Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition, 2022, pp. 2192–2198. https://doi.org/10.1109/icpr56361.2022.9956386.
Chicago
Hu, Yuhuang and Shih‐Chii Liu. 2022. “Kernel Modulation: A Parameter-Efficient Method for Training Convolutional Neural Networks.” Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition: 2192–2198. https://doi.org/10.1109/icpr56361.2022.9956386.
Harvard
Hu, Y. and Liu, S. (2022) ‘Kernel Modulation: A Parameter-Efficient Method for Training Convolutional Neural Networks’, Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition, pp. 2192–2198. doi:10.1109/icpr56361.2022.9956386.
IEEE
Y. Hu and S. Liu, “Kernel Modulation: A Parameter-Efficient Method for Training Convolutional Neural Networks,” Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition, pp. 2192–2198, 2022, doi: 10.1109/icpr56361.2022.9956386.
BibTeX
@inproceedings{hu2022kernel,
title = {{Kernel Modulation: A Parameter-Efficient Method for Training Convolutional Neural Networks}},
author = {Hu, Yuhuang and Liu, Shih‐Chii},
booktitle = {Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition},
year = {2022},
pages = {2192--2198},
doi = {10.1109/icpr56361.2022.9956386},
url = {https://doi.org/10.1109/icpr56361.2022.9956386}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- parameter-efficient training
- convolutional neural networks
- model compression
- transfer learning
- meta-learning
- edge devices
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Hu, Y., & Liu, S. (2022). Kernel Modulation: A Parameter-Efficient Method for Training Convolutional Neural Networks. Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition, 2192–2198. https://doi.org/10.1109/icpr56361.2022.9956386
How many times has this paper been cited?
1 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Yuhuang Hu, Shih‐Chii Liu.
What is the DOI of this paper?
10.1109/icpr56361.2022.9956386, permanently at https://doi.org/10.1109/icpr56361.2022.9956386. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.