Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/167769
Title: Multi-Source Domain Adaptation for Visual Sentiment Classification
Authors: Chuang Lin
Sicheng Zhao
Lei Meng 
Tat-Seng Chua 
Keywords: Computer Vision
Pattern Recognition (cs.CV)
Issue Date: 7-Feb-2020
Citation: Chuang Lin, Sicheng Zhao, Lei Meng, Tat-Seng Chua (2020-02-07). Multi-Source Domain Adaptation for Visual Sentiment Classification. AAAI 2020. ScholarBank@NUS Repository.
Abstract: Existing domain adaptation methods on visual sentiment classification typically are investigated under the singlesource 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-theart MDA approaches for visual sentiment classification.
Source Title: AAAI 2020
URI: https://scholarbank.nus.edu.sg/handle/10635/167769
Appears in Collections:Staff Publications
Elements

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
2001.03886.pdf7.85 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

61
checked on Nov 27, 2020

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.