# Multi-source Domain Adaptation for Visual Sentiment Classification

arXiv: https://arxiv.org/abs/2001.03886 · HTML: https://mlsanity.com/paper/2001.03886/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jan 2020.

## Built on by (most cited first, 16 of 16)

- [Unsupervised Multi-source Domain Adaptation Without Access to Source Data](https://mlsanity.com/paper/2104.01845/) (2021)
- [Affective Image Content Analysis: Two Decades Review and New Perspectives](https://mlsanity.com/paper/2106.16125/) (2021)
- [Cross-Silo Prototypical Calibration for Federated Learning with Non-IID Data](https://mlsanity.com/paper/2308.03457/) (2023)
- [Aggregating From Multiple Target-Shifted Sources](https://mlsanity.com/paper/2105.04051/) (2021)
- [Multimodal Transformer with Variable-length Memory for Vision-and-Language Navigation](https://mlsanity.com/paper/2111.05759/) (2021)
- [Information-theoretic regularization for Multi-source Domain Adaptation](https://mlsanity.com/paper/2104.01568/) (2021)
- [Secure Domain Adaptation with Multiple Sources](https://mlsanity.com/paper/2106.12124/) (2021)
- [More is Better: Deep Domain Adaptation with Multiple Sources](https://mlsanity.com/paper/2405.00749/) (2024)
- [Delving into the Continuous Domain Adaptation](https://mlsanity.com/paper/2208.13121/) (2022)
- [Domain Adaptation for Sentiment Analysis Using Increased Intraclass Separation](https://mlsanity.com/paper/2107.01598/) (2021)
- [Federated Deconfounding and Debiasing Learning for Out-of-Distribution Generalization](https://mlsanity.com/paper/2505.04979/) (2025)
- [EmoCaliber: Advancing Reliable Visual Emotion Comprehension via Confidence Verbalization and Calibration](https://mlsanity.com/paper/2512.15528/) (2025)
- [Global Intervention and Distillation for Federated Out-of-Distribution Generalization](https://mlsanity.com/paper/2504.00850/) (2025)
- [Model Attribution in LLM-Generated Disinformation: A Domain Generalization Approach with Supervised Contrastive Learning](https://mlsanity.com/paper/2407.21264/) (2024)
- [Deep Neural Networks in Video Human Action Recognition: A Review](https://mlsanity.com/paper/2305.15692/) (2023)
- [Analyzing Image Beyond Visual Aspect: Image Emotion Classification via Multiple-Affective Captioning](https://mlsanity.com/paper/2511.23115/) (2025)

## Abstract (arXiv)

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.