Multi-source Domain Adaptation for Visual Sentiment Classification

by   Chuang Lin, et al.
National University of Singapore

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.


page 1

page 4

page 7


Mutual Learning Network for Multi-Source Domain Adaptation

Early Unsupervised Domain Adaptation (UDA) methods have mostly assumed t...

Curriculum CycleGAN for Textual Sentiment Domain Adaptation with Multiple Sources

Sentiment analysis of user-generated reviews or comments on products and...

TriGAN: Image-to-Image Translation for Multi-Source Domain Adaptation

Most domain adaptation methods consider the problem of transferring know...

Improving Domain-Adapted Sentiment Classification by Deep Adversarial Mutual Learning

Domain-adapted sentiment classification refers to training on a labeled ...

Emotional Semantics-Preserved and Feature-Aligned CycleGAN for Visual Emotion Adaptation

Thanks to large-scale labeled training data, deep neural networks (DNNs)...

Learning to Repair Software Vulnerabilities with Generative Adversarial Networks

Motivated by the problem of automated repair of software vulnerabilities...

Text Recognition in Real Scenarios with a Few Labeled Samples

Scene text recognition (STR) is still a hot research topic in computer v...

Please sign up or login with your details

Forgot password? Click here to reset