UDA-HOID: Unsupervised Domain Adaptation for Human-Object Interaction Detection

Miao Jiang, Weiqing Huang, Min Li, Bo Meng, Junxing Ren, Ruwen Bai, Yang Yang

Abstract: Human-object interaction (HOI) detection has witnessed remarkable advancements in recent years, primarily driven by deep learning networks and the availability of large-scale HOI datasets. However, there are still scenarios where HOI detection lacks a suitable training database. The process of expanding existing datasets by manually annotating more images can be challenging because it is time-consuming and labor-intensive. In response to this challenge, domain adaptation has emerged as a promising approach to address the scarcity of annotated data. Drawing inspiration from this, we propose an innovative unsupervised adaptive approach for HOI detection called UDA-HOID. Our method aims to adapt HOI detection from a label-rich source domain to a label-poor target domain, thereby reducing annotation costs and enhancing detection performance. Specifically, UDA-HOID leverages attention-based full alignment for low-level features, which tackles domain shifts caused by image style, illumination, and other factors. Additionally, semantic-based weak alignment is applied to high-level features, as domain shifts in these features contain more semantic information. Adversarial learning techniques are employed to facilitate this alignment process. To evaluate the effectiveness of our proposed method, we conduct experiments on the test data of the low-light HOI image set (LLHOI). The results demonstrate that our approach achieves a relative improvement of 9.8 percent in the mean average precision of roles compared to existing methods.

External IDs:dblp:conf/ictai/JiangHLMRB023