In this paper, we propose a multi-domain learning model for action recognition. The proposed method inserts domain-specific adapters between layers of domain-independent layers of a backbone network. Unlike a multi-head network that switches classification heads only, our model switches not only the heads, but also the adapters for facilitating to learn feature representations universal to multiple domains. Unlike prior works, the proposed method is model-agnostic and doesn't assume model structures unlike prior works. Experimental results on three popular action recognition datasets (HMDB51, UCF101, and Kinetics-400) demonstrate that the proposed method is more effective than a multi-head architecture and more efficient than separately training models for each domain.
翻译:在本文中,我们提出了一个多领域学习行动识别模式。 推荐的方法在主干网中独立领域层之间插入了域特定适应器。 不像一个只开划分类头的多头网络,我们的模型开关不仅包括头部,而且还包括便利学习多领域通用特征描述的适应器。 与先前的工程不同, 推荐的方法是模型不可知性, 不假定与先前的工程不同的模型结构。 三个大众行动识别数据集( HMDB51、 UCF101 和 动因- 400)的实验结果显示, 拟议的方法比多头结构更有效, 比每个领域的单独培训模式更有效。