Zero-shot domain adaptation (ZDA) methods aim to transfer knowledge about a task learned in a source domain to a target domain, while data from target domain are not available. In this work, we address learning feature representations which are invariant to and shared among different domains considering task characteristics for ZDA. To this end, we propose a method for task-guided ZDA (TG-ZDA) which employs multi-branch deep neural networks to learn feature representations exploiting their domain invariance and shareability properties. The proposed TG-ZDA models can be trained end-to-end without requiring synthetic tasks and data generated from estimated representations of target domains. The proposed TG-ZDA has been examined using benchmark ZDA tasks on image classification datasets. Experimental results show that our proposed TG-ZDA outperforms state-of-the-art ZDA methods for different domains and tasks.
翻译:零光域适应(ZDA)方法旨在向目标领域转让有关在源领域学习的任务的知识,而目标领域的数据则无法提供。在这项工作中,我们处理不同领域之间不同和共享的学习特征表现,同时考虑到ZDA的任务特点。为此,我们提议了一个任务引导ZDA(TG-ZDA)方法,该方法采用多分支深层神经网络,学习利用其域差异和共享特性的特征表现。拟议的TG-ZDA模型可以培训端到端,而不需要合成任务和目标领域估计显示产生的数据。拟议的TG-ZDA方法已经利用基准ZDA关于图像分类数据集的任务进行了审查。实验结果显示,我们提议的TG-ZDA在不同的领域和任务中超越了最新的ZDA方法。