DecAug: Augmenting HOI Detection via Decomposition

TL;DR

DecAug is a novel data augmentation technique for human-object interaction detection that enhances training data by sharing object patterns and reconfiguring spatial relationships, leading to significant performance improvements.

Contribution

We introduce DecAug, a new augmentation method utilizing object similarity and pose-guided spatial shifts to improve HOI detection accuracy.

Findings

Up to 3.3 mAP improvement on V-COCO dataset

Up to 1.6 mAP improvement on HICODET dataset

More notable gains for interactions with fewer samples

Abstract

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.