Task guided representation learning using compositional models for zero-shot domain adaptation

Shuang Liu

doi:10.1016/j.neunet.2023.05.030

Task guided representation learning using compositional models for zero-shot domain adaptation

2023-08-01

2

PRE

AI

DOI：10.1016/j.neunet.2023.05.030

Original

Original request for help

Save

Abstract

En 中文

Zero-shot domain adaptation (ZDA) methods aim to transfer knowledge about a task learned in a source domain to a target domain, while task-relevant 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 represen-tations 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.& COPY; 2023 Elsevier Ltd. All rights reserved.

Keywords:

Domain adaptation

Zero-shot

Representation learning

Task guided representation learning using compositional models for zero-shot domain adaptation

Abstract

Journal

Organization