BayesVQA: Energy-Guided Bayesian Debiasing for Language-Bias-Robust Visual Question Answering
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (7) · 5221-5229
DOI: 10.1609/aaai.v40i7.37437 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zhiqi Huang und 4 weiteren Autor:innen.
Abstract (Originalsprache)
Numerous studies have demonstrated that Visual Question Answering (VQA) models are vulnerable to language priors and dataset biases, often leading to spurious correlations between questions and answers. As a result, these models excessively rely on linguistic cues, neglecting essential visual information and causing representational distortions. To address this challenge, we propose a novel Bayesian debiasing framework termed BayesVQA, which integrates three carefully designed mechanisms: Energy-guided Prior Variance (EPV), Energy-guided Posterior Sampling (EPS), and Energy-guided Likelihood Reweighting (ELR). Specifically, we explicitly decompose each sample's latent representation into a biased feature and a stochastic corrective perturbation δ. Using a Bayesian formulation, we model the posterior distribution of the perturbation δ conditioned on the predictive uncertainty, quantified via calibrated energy scores. To mitigate language bias, the posterior is optimized through energy-driven variational inference with an uncertainty-adaptive prior and sampling strategy. Moreover, the ELR mechanism incorporates an energy-based weighting of the reconstruction objective and enforces an energy-coherence constraint to emphasize challenging, high-uncertainty instances and align model confidence before and after debiasing. Extensive experiments conducted across multiple standard VQA benchmarks consistently validate the superior performance of our BayesVQA method over state-of-the-art competitors under distributional shifts and challenging bias conditions.
Zitieren
APA
Huang, Z., Zhu, H., Deng, X., Qinghao, Z., & Chen, B. (2026). BayesVQA: Energy-Guided Bayesian Debiasing for Language-Bias-Robust Visual Question Answering. Proceedings of the AAAI Conference on Artificial Intelligence, 40(7), 5221-5229. https://doi.org/10.1609/aaai.v40i7.37437
Vancouver
Huang Z, Zhu H, Deng X, Qinghao Z, Chen B. BayesVQA: Energy-Guided Bayesian Debiasing for Language-Bias-Robust Visual Question Answering. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(7):5221-5229. doi:10.1609/aaai.v40i7.37437
BibTeX
@article{Huang2026,
author = {Huang, Zhiqi and Zhu, Huanjia and Deng, Xiangwen and Qinghao, Zhong and Chen, Bingzhi},
title = {BayesVQA: Energy-Guided Bayesian Debiasing for Language-Bias-Robust Visual Question Answering},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {7},
pages = {5221--5229},
doi = {10.1609/aaai.v40i7.37437}
}
EUVIMED