Debiasing vision-language models for vision tasks: a survey

Graphical abstract

References

[1] Radford A, Kim J W, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J, Krueger G, Sutskever I. Learning transferable visual models from natural language supervision. In: Proceedings of the 38th International Conference on Machine Learning. 2021, 8748–8763

[2] Seth A, Hemani M, Agarwal C. DeAR: debiasing vision-language models with additive residuals. In: Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023, 6820–6829

[3] Zhu B, Tang K, Sun Q, Zhang H. Generalized logit adjustment: Calibrating fine-tuned models by removing label bias in foundation models. In: Proceedings of the 37th Conference on Neural Information Processing Systems. 2023, 64663–64680

[4] Allingham J U, Ren J, Dusenberry M W, Gu X, Cui Y, Tran D, Liu J Z, Lakshminarayanan B. A simple zero-shot prompt weighting technique to improve prompt ensembling in text-image models. In: Proceedings of the 40th International Conference on Machine Learning. 2023, 26

[5] Wang J, Liu Y, Wang X. Are gender-neutral queries really gender-neutral? Mitigating gender bias in image search. In: Proceedings of 2021 Conference on Empirical Methods in Natural Language Processing. 2021, 1995–2008

[6] Wang X, Wu Z, Lian L, Yu S X. Debiased learning from naturally imbalanced pseudo-labels. In: Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022, 14627–14637

[7] Cui J, Zhu B, Wen X, Qi X, Yu B, Zhang H. Classes are not equal: an empirical study on image recognition fairness. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2024, 23283–23292

[8] Zhu B, Niu Y, Lee S, Hur M, Zhang H. Debiased fine-tuning for vision-language models by prompt regularization. In: Proceedings of the 37th AAAI Conference on Artificial Intelligence. 2023, 3834–3842

[9] Zhang M, Ré C. Contrastive adapters for foundation model group robustness. In: Proceedings of the 36th International Conference on Neural Information Processing Systems. 2022, 1576

[10] Chuang C Y, Jampani V, Li Y, Torralba A, Jegelka S. Debiasing vision-language models via biased prompts. 2023, arXiv preprint arXiv: 2302.00070

[11] Parashar S, Lin Z, Liu T, Dong X, Li Y, Ramanan D, Caverlee J, Kong S. The neglected tails in vision-language models. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024, 12988–12997

[12] Berg H, Hall S, Bhalgat Y, Kirk H, Shtedritski A, Bain M. A prompt array keeps the bias away: Debiasing vision-language models with adversarial learning. In: Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing. 2022, 806–822

Competing interests

The authors declare that they have no competing interests or financial conflicts to disclose.

RIGHTS & PERMISSIONS

2025 Higher Education Press