Conference paper · 2023 · Open access

Fully Attentional Networks with Self-emerging Token Labeling

Bingyin Zhao, Zhiding Yu, Shiyi Lan, Yutao Cheng, Animashree Anandkumar, Yingjie Lao, José Manuel Álvarez

IEEE/CVF International Conference on Computer Vision (ICCV), 5562–5572 · Published 1 October 2023 · DOI 10.1109/iccv51070.2023.00514

Open PDFView at the publisherCite this paper

In brief

“Fully Attentional Networks with Self-emerging Token Labeling” is a 2023 conference paper by Bingyin Zhao and 6 co-authors, published in IEEE/CVF International Conference on Computer Vision (ICCV). OpenAlex counts 7 citations as of 22 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
7
Most cited in
2024 (3)
Field-weighted impact
0.41
References
64
Authors
7

Abstract

Recent studies indicate that Vision Transformers (ViTs) are robust against out-of-distribution scenarios. In particular, the Fully Attentional Network (FAN) - a family of ViT backbones, has achieved state-of-the-art robustness. In this paper, we revisit the FAN models and improve their pretraining with a self-emerging token labeling (STL) framework. Our method contains a two-stage training framework. Specifically, we first train a FAN token labeler (FAN-TL) to generate semantically meaningful patch token labels, followed by a FAN student model training stage that uses both the token labels and the original class label. With the proposed STL framework, our best model based on FANL-Hybrid (77.3M parameters) achieves 84.8% Top-1 accuracy and 42.1% mCE on ImageNet-1K and ImageNetC, and sets a new state-of-the-art for ImageNet-A (46.1%) and ImageNet-R (56.6%) without using extra data, outperforming the original FAN counterpart by significant margins. The proposed framework also demonstrates significantly enhanced performance on downstream tasks such as semantic segmentation, with up to 1.7% improvement in robustness over the counterpart model.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Zhao, B., Yu, Z., Lan, S., Cheng, Y., Anandkumar, A., Lao, Y., & Álvarez, J. M. (2023). Fully Attentional Networks with Self-emerging Token Labeling. IEEE/CVF International Conference on Computer Vision (ICCV), 5562–5572. https://doi.org/10.1109/iccv51070.2023.00514

MLA 9

Zhao, Bingyin, et al. “Fully Attentional Networks with Self-emerging Token Labeling.” IEEE/CVF International Conference on Computer Vision (ICCV), 2023, pp. 5562–5572. https://doi.org/10.1109/iccv51070.2023.00514.

Chicago

Zhao, Bingyin, Zhiding Yu, Shiyi Lan, Yutao Cheng, Animashree Anandkumar, Yingjie Lao, and José Manuel Álvarez. 2023. “Fully Attentional Networks with Self-emerging Token Labeling.” IEEE/CVF International Conference on Computer Vision (ICCV): 5562–5572. https://doi.org/10.1109/iccv51070.2023.00514.

Harvard

Zhao, B. et al. (2023) ‘Fully Attentional Networks with Self-emerging Token Labeling’, IEEE/CVF International Conference on Computer Vision (ICCV), pp. 5562–5572. doi:10.1109/iccv51070.2023.00514.

IEEE

B. Zhao et al., “Fully Attentional Networks with Self-emerging Token Labeling,” IEEE/CVF International Conference on Computer Vision (ICCV), pp. 5562–5572, 2023, doi: 10.1109/iccv51070.2023.00514.

BibTeX

@inproceedings{zhao2023fully,
  title     = {{Fully Attentional Networks with Self-emerging Token Labeling}},
  author    = {Zhao, Bingyin and Yu, Zhiding and Lan, Shiyi and Cheng, Yutao and Anandkumar, Animashree and Lao, Yingjie and Álvarez, José Manuel},
  booktitle = {IEEE/CVF International Conference on Computer Vision (ICCV)},
  year      = {2023},
  pages     = {5562--5572},
  doi       = {10.1109/iccv51070.2023.00514},
  url       = {https://doi.org/10.1109/iccv51070.2023.00514}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202433
202533
202611

Its field-weighted citation impact is 0.41: it has been cited 0.41 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications

  • vision transformer
  • out-of-distribution robustness
  • pre-training
  • ImageNet-C
  • semantic segmentation
  • two-stage training

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Zhao, B., Yu, Z., Lan, S., Cheng, Y., Anandkumar, A., Lao, Y., & Álvarez, J. M. (2023). Fully Attentional Networks with Self-emerging Token Labeling. IEEE/CVF International Conference on Computer Vision (ICCV), 5562–5572. https://doi.org/10.1109/iccv51070.2023.00514

How many times has this paper been cited?

7 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?

Bingyin Zhao, Zhiding Yu, Shiyi Lan, Yutao Cheng, Animashree Anandkumar, Yingjie Lao, José Manuel Álvarez.

What is the DOI of this paper?

10.1109/iccv51070.2023.00514, permanently at https://doi.org/10.1109/iccv51070.2023.00514. 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.