论文标题
depaug：通过分解增强HOI检测
DecAug: Augmenting HOI Detection via Decomposition
论文作者
论文摘要
人类对象相互作用（HOI）检测需要大量注释的数据。当前的算法遭受了数据集中培训样本和类别不平衡的不足。为了提高数据效率，在本文中，我们提出了一种称为HOI检测depaug的高效数据增强方法。基于我们提出的对象状态相似性度量，共享不同HOI的对象模式以增强本地对象外观特征而不改变其状态。此外，我们借助姿势引导的高斯混合模型将人与物体之间的空间相关性转移到其他可行的配置，同时保持其相互作用。实验表明，对于两个高级模型，我们的方法在V-Coco和Hicodet数据集上提供了高达3.3 MAP和1.6 MAP改进。具体来说，与较少样本的互动享有更明显的改进。我们的方法可以轻松地集成到各种HOI检测模型中，并可以忽略不计的额外计算消耗。我们的代码将公开可用。
Human-object interaction (HOI) detection requires a large amount of annotated data. Current algorithms suffer from insufficient training samples and category imbalance within datasets. To increase data efficiency, in this paper, we propose an efficient and effective data augmentation method called DecAug for HOI detection. Based on our proposed object state similarity metric, object patterns across different HOIs are shared to augment local object appearance features without changing their state. Further, we shift spatial correlation between humans and objects to other feasible configurations with the aid of a pose-guided Gaussian Mixture Model while preserving their interactions. Experiments show that our method brings up to 3.3 mAP and 1.6 mAP improvements on V-COCO and HICODET dataset for two advanced models. Specifically, interactions with fewer samples enjoy more notable improvement. Our method can be easily integrated into various HOI detection models with negligible extra computational consumption. Our code will be made publicly available.
