DecAug: Augmenting HOI Detection via Decomposition
This addresses data efficiency issues for researchers and practitioners in computer vision, but it is incremental as it builds on existing HOI detection models.
The paper tackles the problem of insufficient training data and category imbalance in human-object interaction (HOI) detection by proposing DecAug, a data augmentation method that improves detection performance by up to 3.3 mAP on V-COCO and 1.6 mAP on HICODET datasets.
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.