Preprint · 2020 · Open access
Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network
arXiv (Cornell University) · Published 17 January 2020 · DOI 10.48550/arxiv.2001.06268
In brief
“Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network” is a 2020 preprint by Jungkyu Lee and 5 co-authors, published in arXiv (Cornell University). OpenAlex counts 67 citations as of 18 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 67
- Most cited in
- 2021 (20)
- References
- 40
- Authors
- 6
Abstract
Recent studies in image classification have demonstrated a variety of techniques for improving the performance of Convolutional Neural Networks (CNNs). However, attempts to combine existing techniques to create a practical model are still uncommon. In this study, we carry out extensive experiments to validate that carefully assembling these techniques and applying them to basic CNN models (e.g. ResNet and MobileNet) can improve the accuracy and robustness of the models while minimizing the loss of throughput. Our proposed assembled ResNet-50 shows improvements in top-1 accuracy from 76.3\% to 82.78\%, mCE from 76.0\% to 48.9\% and mFR from 57.7\% to 32.3\% on ILSVRC2012 validation set. With these improvements, inference throughput only decreases from 536 to 312. To verify the performance improvement in transfer learning, fine grained classification and image retrieval tasks were tested on several public datasets and showed that the improvement to backbone network performance boosted transfer learning performance significantly. Our approach achieved 1st place in the iFood Competition Fine-Grained Visual Recognition at CVPR 2019, and the source code and trained models are available at https://github.com/clovaai/assembled-cnn
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Lee, J., Won, T., Lee, T. K., Lee, H., Gu, G., & Hong, K. (2020). Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2001.06268
MLA 9
Lee, Jungkyu, et al. “Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network.” arXiv (Cornell University), 2020. https://doi.org/10.48550/arxiv.2001.06268.
Chicago
Lee, Jungkyu, Taeryun Won, Tae Kwan Lee, Hyemin Lee, Geonmo Gu, and Kiho Hong. 2020. “Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2001.06268.
Harvard
Lee, J. et al. (2020) ‘Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network’, arXiv (Cornell University). doi:10.48550/arxiv.2001.06268.
IEEE
J. Lee, T. Won, T. K. Lee, H. Lee, G. Gu, and K. Hong, “Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network,” arXiv (Cornell University), 2020, doi: 10.48550/arxiv.2001.06268.
BibTeX
@misc{lee2020compounding,
title = {{Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network}},
author = {Lee, Jungkyu and Won, Taeryun and Lee, Tae Kwan and Lee, Hyemin and Gu, Geonmo and Hong, Kiho},
howpublished = {arXiv (Cornell University)},
year = {2020},
doi = {10.48550/arxiv.2001.06268},
url = {https://doi.org/10.48550/arxiv.2001.06268}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2020 | 9 | |
| 2021 | 20 | |
| 2022 | 18 | |
| 2023 | 7 | |
| 2024 | 6 | |
| 2025 | 4 | |
| 2026 | 3 |
Topic and keywords
Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- convolutional neural networks
- ResNet50
- MobileNet
- model assembly
- image classification
- transfer learning
- fine-grained visual recognition
- image retrieval
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?
Lee, J., Won, T., Lee, T. K., Lee, H., Gu, G., & Hong, K. (2020). Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2001.06268
How many times has this paper been cited?
67 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?
Jungkyu Lee, Taeryun Won, Tae Kwan Lee, Hyemin Lee, Geonmo Gu, Kiho Hong.
What is the DOI of this paper?
10.48550/arxiv.2001.06268, permanently at https://doi.org/10.48550/arxiv.2001.06268. 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.