论文标题
突出显示对象类别的免疫力，用于概括人类对象互动检测
Highlighting Object Category Immunity for the Generalization of Human-Object Interaction Detection
论文作者
论文摘要
人对象相互作用（HOI）检测在活动理解中起核心作用。作为一个组成学习问题（人类动物对象），研究其概括事项。但是，广泛使用的度量平均平均精度（MAP）无法很好地对组成概括进行建模。因此，我们提出了一种新颖的度量，MPD（平均性能降低），作为MAP的补充，以评估不同对象和相同动词的组成之间的性能差距。出乎意料的是，MPD揭示了以前的方法通常概括不佳。以MPD作为提示，我们建议对象类别（OC）免疫来增强HOI概括。这个想法是防止模型学习虚假的对象 - 动词相关性，以换取火车集的缩短。为了实现OC免疫性，我们提出了一个OC-免疫网络，该网络将输入与OC分解，提取OC-免疫表示形式，并利用不确定性量化以推广到看不见的对象。在常规和零拍实验中，我们的方法可实现不错的改进。为了充分评估概括，我们设计了一个新的，更困难的基准，我们在其上具有重要的优势。该代码可在https://github.com/foruck/oc-immunity上找到。
Human-Object Interaction (HOI) detection plays a core role in activity understanding. As a compositional learning problem (human-verb-object), studying its generalization matters. However, widely-used metric mean average precision (mAP) fails to model the compositional generalization well. Thus, we propose a novel metric, mPD (mean Performance Degradation), as a complementary of mAP to evaluate the performance gap among compositions of different objects and the same verb. Surprisingly, mPD reveals that previous methods usually generalize poorly. With mPD as a cue, we propose Object Category (OC) Immunity to boost HOI generalization. The idea is to prevent model from learning spurious object-verb correlations as a short-cut to over-fit the train set. To achieve OC-immunity, we propose an OC-immune network that decouples the inputs from OC, extracts OC-immune representations, and leverages uncertainty quantification to generalize to unseen objects. In both conventional and zero-shot experiments, our method achieves decent improvements. To fully evaluate the generalization, we design a new and more difficult benchmark, on which we present significant advantage. The code is available at https://github.com/Foruck/OC-Immunity.
