HQD-EM: Robust VQA Through Hierarchical Question Decomposition Bias Module and Ensemble Adaptive Angular Margin Loss
Recent studies in Visual Question Answering (VQA) have revealed that models often rely heavily on language priors rather than vision–language understanding, leading to poor generalization under distribution shifts. To address this challenge, we propose HQD-EM, a unified debiasing framework that comb...
Guardat en:
| Autors principals: | , |
|---|---|
| Format: | Artigo |
| Idioma: | Inglês |
| Publicat: |
MDPI AG
2025-11-01
|
| Col·lecció: | Mathematics |
| Matèries: | |
| Accés en línia: | https://www.mdpi.com/2227-7390/13/22/3656 |
| Etiquetes: |
Sense etiquetes, Sigues el primer a etiquetar aquest registre!
|