Task Guided Compositional Representation Learning for ZDA
This addresses domain adaptation for image classification when target domain data is unavailable, but it appears incremental as it builds on existing ZDA approaches.
The paper tackles zero-shot domain adaptation (ZDA) by proposing a task-guided method (TG-ZDA) that learns domain-invariant and shareable feature representations using multi-branch neural networks, and it outperforms state-of-the-art methods on benchmark image classification tasks.
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.