Preprint · 2021 · Open access
Vision Transformer for Small-Size Datasets
arXiv (Cornell University) · Published 27 December 2021 · DOI 10.48550/arxiv.2112.13492
In brief
“Vision Transformer for Small-Size Datasets” is a 2021 preprint by Seung Hoon Lee and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 362 citations as of 22 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 362
- Most cited in
- 2024 (107)
- References
- 33
- Authors
- 3
Abstract
Recently, the Vision Transformer (ViT), which applied the transformer structure to the image classification task, has outperformed convolutional neural networks. However, the high performance of the ViT results from pre-training using a large-size dataset such as JFT-300M, and its dependence on a large dataset is interpreted as due to low locality inductive bias. This paper proposes Shifted Patch Tokenization (SPT) and Locality Self-Attention (LSA), which effectively solve the lack of locality inductive bias and enable it to learn from scratch even on small-size datasets. Moreover, SPT and LSA are generic and effective add-on modules that are easily applicable to various ViTs. Experimental results show that when both SPT and LSA were applied to the ViTs, the performance improved by an average of 2.96% in Tiny-ImageNet, which is a representative small-size dataset. Especially, Swin Transformer achieved an overwhelming performance improvement of 4.08% thanks to the proposed SPT and LSA.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Lee, S. H., Seunghyun, L., & Song, B. C. (2021). Vision Transformer for Small-Size Datasets. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2112.13492
MLA 9
Lee, Seung Hoon, et al. “Vision Transformer for Small-Size Datasets.” arXiv (Cornell University), 2021. https://doi.org/10.48550/arxiv.2112.13492.
Chicago
Lee, Seung Hoon, Lee, Seunghyun, and Byung Cheol Song. 2021. “Vision Transformer for Small-Size Datasets.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2112.13492.
Harvard
Lee, S. H., Seunghyun, L. and Song, B. C. (2021) ‘Vision Transformer for Small-Size Datasets’, arXiv (Cornell University). doi:10.48550/arxiv.2112.13492.
IEEE
S. H. Lee, L. Seunghyun, and B. C. Song, “Vision Transformer for Small-Size Datasets,” arXiv (Cornell University), 2021, doi: 10.48550/arxiv.2112.13492.
BibTeX
@misc{lee2021vision,
title = {{Vision Transformer for Small-Size Datasets}},
author = {Lee, Seung Hoon and Seunghyun, Lee, and Song, Byung Cheol},
howpublished = {arXiv (Cornell University)},
year = {2021},
doi = {10.48550/arxiv.2112.13492},
url = {https://doi.org/10.48550/arxiv.2112.13492}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2012 | 1 | |
| 2019 | 1 | |
| 2022 | 37 | |
| 2023 | 80 | |
| 2024 | 107 | |
| 2025 | 78 | |
| 2026 | 58 |
Topic and keywords
Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- vision transformer
- self-supervised pre-training
- Tiny ImageNet
- Swin Transformer
- image classification
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, S. H., Seunghyun, L., & Song, B. C. (2021). Vision Transformer for Small-Size Datasets. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2112.13492
How many times has this paper been cited?
362 times, according to OpenAlex on 22 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?
Seung Hoon Lee, Lee, Seunghyun, Byung Cheol Song.
What is the DOI of this paper?
10.48550/arxiv.2112.13492, permanently at https://doi.org/10.48550/arxiv.2112.13492. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 22 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.