量子模型QPredSGG提升场景图生成性能

作者 PulseAugur 编辑部 · [2 个来源] · 2026-06-03 10:15

研究人员开发了一种混合量子经典模型QPredSGG，通过解决谓词关系的长尾不平衡问题来改进场景图生成。该模型用量子谓词头（QP-Head）替换了CFEN架构中的经典谓词头。与经典模型相比，QP-Head在显著减少可训练参数数量的同时，实现了更高的平均召回率（mR@100）。 AI

影响为复杂的视觉推理任务引入了一种参数高效的量子方法，有可能提高在代表性不足数据上的性能。

排序理由这是一篇详细介绍用于特定AI任务的新型混合量子经典模型的学术论文。 [lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.LG TIER_1 English(EN) · Prerana Ramkumar, Nouhaila Innan, Muhammad Shafique · 2026-06-04 04:00

QPredSGG: Hybrid Quantum Predicate Learning for Long-Tailed Scene Graph Generation

arXiv:2606.04689v1 Announce Type: cross Abstract: Scene Graph Generation (SGG) requires relational reasoning over objects and their interactions, but performance is often limited by severe long-tail predicate imbalance. Classical SGG models frequently rely on dataset statistics, …
arXiv cs.LG TIER_1 English(EN) · Muhammad Shafique · 2026-06-03 10:15

QPredSGG: Hybrid Quantum Predicate Learning for Long-Tailed Scene Graph Generation

Scene Graph Generation (SGG) requires relational reasoning over objects and their interactions, but performance is often limited by severe long-tail predicate imbalance. Classical SGG models frequently rely on dataset statistics, leading to biased predictions toward frequent rela…