Cross-Domain Adversarial Auto-Encoder
This work addresses cross-domain image processing for applications like domain adaptation, offering a method that handles both labeled and unlabeled data, but it appears incremental as it builds on existing adversarial auto-encoder concepts.
The paper tackles cross-domain image inference, generation, and transformation by proposing a framework that assumes shared content and separate style latent spaces, enabling generation of diverse samples across domains while maintaining content consistency. Experimental results on SVHN, MNIST, and CASIA datasets show visually appealing image generation and superior performance in domain adaptation tasks.
In this paper, we propose the Cross-Domain Adversarial Auto-Encoder (CDAAE) to address the problem of cross-domain image inference, generation and transformation. We make the assumption that images from different domains share the same latent code space for content, while having separate latent code space for style. The proposed framework can map cross-domain data to a latent code vector consisting of a content part and a style part. The latent code vector is matched with a prior distribution so that we can generate meaningful samples from any part of the prior space. Consequently, given a sample of one domain, our framework can generate various samples of the other domain with the same content of the input. This makes the proposed framework different from the current work of cross-domain transformation. Besides, the proposed framework can be trained with both labeled and unlabeled data, which makes it also suitable for domain adaptation. Experimental results on data sets SVHN, MNIST and CASIA show the proposed framework achieved visually appealing performance for image generation task. Besides, we also demonstrate the proposed method achieved superior results for domain adaptation. Code of our experiments is available in https://github.com/luckycallor/CDAAE.