Multi-source Domain Adaptation for Visual Sentiment Classification
This work addresses the challenge of improving visual sentiment classification accuracy for applications like social media analysis by leveraging multiple source domains, though it is incremental as it builds on existing domain adaptation methods.
The paper tackles the problem of limited data coverage in single-source domain adaptation for visual sentiment classification by proposing a multi-source domain adaptation method called MSGAN, which learns a unified sentiment latent space via adversarial learning and significantly outperforms state-of-the-art approaches on four benchmark datasets.
Existing domain adaptation methods on visual sentiment classification typically are investigated under the single-source scenario, where the knowledge learned from a source domain of sufficient labeled data is transferred to the target domain of loosely labeled or unlabeled data. However, in practice, data from a single source domain usually have a limited volume and can hardly cover the characteristics of the target domain. In this paper, we propose a novel multi-source domain adaptation (MDA) method, termed Multi-source Sentiment Generative Adversarial Network (MSGAN), for visual sentiment classification. To handle data from multiple source domains, it learns to find a unified sentiment latent space where data from both the source and target domains share a similar distribution. This is achieved via cycle consistent adversarial learning in an end-to-end manner. Extensive experiments conducted on four benchmark datasets demonstrate that MSGAN significantly outperforms the state-of-the-art MDA approaches for visual sentiment classification.