Journal article · 2026 · Open access

Bridging the Gap Between Active Learning and Pseudolabel Learning for Vision–Language Models

Yanchao Li, Yongjie Lai, Guangwei Gao, Chia‐Wen Lin

IEEE Transactions on Neural Networks and Learning Systems, PP, 1–15 · Published 30 October 2026 · DOI 10.1109/tnnls.2026.3738447

Open full textCite this paper

In brief

“Bridging the Gap Between Active Learning and Pseudolabel Learning for Vision–Language Models” is a 2026 journal article by Yanchao Li and 3 co-authors, published in IEEE Transactions on Neural Networks and Learning Systems. OpenAlex counts 0 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at IEEE Transactions on Neural Networks and Learning Systems.

Citations
0
Authors
4

Abstract

Recent studies have explored enhancing label efficiency in vision-language models (VLMs) for downstream tasks. Existing methods of pseudolabel learning (PL) would suffer from heavily incorrect hard pseudolabels. Nevertheless, active learning (AL) focuses on uncertain samples that can cause forgetting of VLMs' existing knowledge. Can these two paradigms work together to enhance the performance of VLMs? To alleviate the issues mentioned above, we bridge the gap between the two via a resampling mechanism that balances the data distribution without increasing labeling costs. By offering a comprehensive and well-distributed labeled set, the downstream task models based on VLMs receive balanced gradient updates during training, which helps to reduce miscalibration and overfitting in models. Comprehensive experimental results demonstrate the effectiveness and general applicability of our method compared to state-of-the-art label-efficient approaches with VLMs across several benchmark datasets.

Cite this paper

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

APA 7

Li, Y., Lai, Y., Gao, G., & Lin, C. (2026). Bridging the Gap Between Active Learning and Pseudolabel Learning for Vision–Language Models. IEEE Transactions on Neural Networks and Learning Systems, PP, 1–15. https://doi.org/10.1109/tnnls.2026.3738447

MLA 9

Li, Yanchao, et al. “Bridging the Gap Between Active Learning and Pseudolabel Learning for Vision–Language Models.” IEEE Transactions on Neural Networks and Learning Systems, vol. PP, 2026, pp. 1–15. https://doi.org/10.1109/tnnls.2026.3738447.

Chicago

Li, Yanchao, Yongjie Lai, Guangwei Gao, and Chia‐Wen Lin. 2026. “Bridging the Gap Between Active Learning and Pseudolabel Learning for Vision–Language Models.” IEEE Transactions on Neural Networks and Learning Systems PP: 1–15. https://doi.org/10.1109/tnnls.2026.3738447.

Harvard

Li, Y. et al. (2026) ‘Bridging the Gap Between Active Learning and Pseudolabel Learning for Vision–Language Models’, IEEE Transactions on Neural Networks and Learning Systems, PP, pp. 1–15. doi:10.1109/tnnls.2026.3738447.

IEEE

Y. Li, Y. Lai, G. Gao, and C. Lin, “Bridging the Gap Between Active Learning and Pseudolabel Learning for Vision–Language Models,” IEEE Transactions on Neural Networks and Learning Systems, vol. PP, pp. 1–15, 2026, doi: 10.1109/tnnls.2026.3738447.

BibTeX

@article{li2026bridging,
  title     = {{Bridging the Gap Between Active Learning and Pseudolabel Learning for Vision–Language Models}},
  author    = {Li, Yanchao and Lai, Yongjie and Gao, Guangwei and Lin, Chia‐Wen},
  journal   = {IEEE Transactions on Neural Networks and Learning Systems},
  year      = {2026},
  volume    = {PP},
  pages     = {1--15},
  doi       = {10.1109/tnnls.2026.3738447},
  url       = {https://doi.org/10.1109/tnnls.2026.3738447}
}

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

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications

  • active learning (machine learning)
  • vision-language models
  • label efficiency
  • calibration error
  • overfitting
  • knowledge forgetting

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?

Li, Y., Lai, Y., Gao, G., & Lin, C. (2026). Bridging the Gap Between Active Learning and Pseudolabel Learning for Vision–Language Models. IEEE Transactions on Neural Networks and Learning Systems, PP, 1–15. https://doi.org/10.1109/tnnls.2026.3738447

How many times has this paper been cited?

0 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 IEEE Transactions on Neural Networks and Learning Systems: sign in and open the full text from this page.

Who wrote this paper?

Yanchao Li, Yongjie Lai, Guangwei Gao, Chia‐Wen Lin.

What is the DOI of this paper?

10.1109/tnnls.2026.3738447, permanently at https://doi.org/10.1109/tnnls.2026.3738447. 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.