论文标题
具有域特异性适配器的模型不合时宜的多域学习用于行动识别
Model-agnostic Multi-Domain Learning with Domain-Specific Adapters for Action Recognition
论文作者
论文摘要
在本文中，我们提出了一个多域学习模型，以供行动识别。所提出的方法在骨干网络的域独立层层之间插入域特异性适配器。与仅切换分类头的多头网络不同，我们的模型不仅要切换头部，还可以切换用于促进的适配器，以学习为多个域通用的特征表示形式。与先前的工作不同，所提出的方法是模型不可静止的，并且不假定与先前的作品不同的模型结构。对三个流行动作识别数据集（HMDB51，UCF101和Kinetics-400）的实验结果表明，所提出的方法比多头体系结构更有效，并且比为每个域分别训练模型更有效。
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.
