DecAug: Augmenting HOI Detection via Decomposition


  • Hao-Shu Fang Shanghai Jiao Tong University
  • Yichen Xie Shanghai Jiao Tong University
  • Dian Shao The Chinese University of Hong Kong
  • Yong-Lu Li Shanghai Jiao Tong University
  • Cewu Lu Shanghai Jiao Tong University



Scene Analysis & Understanding, Video Understanding & Activity Analysis, Language and Vision


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 states. 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 HICO-DET 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.




How to Cite

Fang, H.-S., Xie, Y., Shao, D., Li, Y.-L., & Lu, C. (2021). DecAug: Augmenting HOI Detection via Decomposition. Proceedings of the AAAI Conference on Artificial Intelligence, 35(2), 1300-1308.



AAAI Technical Track on Computer Vision I