BUSSARD：基于归一化流的生物jective通用场景特定异常关系检测
BUSSARD: Normalizing Flows for Bijective Universal Scene-Specific Anomalous Relationship Detection
AI总结：
本文提出BUSSARD模型，通过归一化流学习场景图中对象-关系-对象三元组到基础分布的可逆变换，实现异常关系检测。在SARD数据集上取得优于当前SOTA的AUROC提升，并展示出更强的鲁棒性和通用性。
摘要：
我们提出了Bijective Universal Scene-Specific Anomalous Relationship Detection (BUSSARD)，一种基于归一化流的模型，用于检测从图像生成的场景图中的异常关系。我们的方法采用多模态方法，通过语言模型嵌入场景图中的对象和关系标记，以利用现实世界的语义知识。归一化流模型用于学习将场景图中的对象-关系-对象三元组映射到简单基础分布（通常为高斯分布）的可逆变换，从而通过似然估计进行异常检测。我们在包含办公和餐厅场景的SARD数据集上评估了我们的方法。与当前最先进的模型相比，我们的方法在AUROC上提高了约10%，同时运行速度提高了五倍。通过消融研究，我们展示了更强的鲁棒性和通用性，特别是在处理同义词时，我们的模型保持稳定性能，而基线模型表现出17.5%的偏差。这项工作展示了基于学习的方法在场景图关系异常检测中的强大潜力。我们的代码可在https://github.com/mschween/BUSSARD上获得。
英文摘要：
We propose Bijective Universal Scene-Specific Anomalous Relationship Detection (BUSSARD), a normalizing flow-based model for detecting anomalous relations in scene graphs, generated from images. Our work follows a multimodal approach, embedding object and relationship tokens from scene graphs with a language model to leverage semantic knowledge from the real world. A normalizing flow model is used to learn bijective transformations that map object-relation-object triplets from scene graphs to a simple base distribution (typically Gaussian), allowing anomaly detection through likelihood estimation. We evaluate our approach on the SARD dataset containing office and dining room scenes. Our method achieves around 10% better AUROC results compared to the current state-of-the-art model, while simultaneously being five times faster. Through ablation studies, we demonstrate superior robustness and universality, particularly regarding the use of synonyms, with our model maintaining stable performance while the baseline shows 17.5% deviation. This work demonstrates the strong potential of learning-based methods for relationship anomaly detection in scene graphs. Our code is available at https://github.com/mschween/BUSSARD .
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
