@inproceedings{xu-etal-2020-open,
title = "Open-Ended Visual Question Answering by Multi-Modal Domain Adaptation",
author = "Xu, Yiming and
Chen, Lin and
Cheng, Zhongwei and
Duan, Lixin and
Luo, Jiebo",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.34/",
doi = "10.18653/v1/2020.findings-emnlp.34",
pages = "367--376",
abstract = "We study the problem of visual question answering (VQA) in images by exploiting supervised domain adaptation, where there is a large amount of labeled data in the source domain but only limited labeled data in the target domain, with the goal to train a good target model. A straightforward solution is to fine-tune a pre-trained source model by using those limited labeled target data, but it usually cannot work well due to the considerable difference between the data distributions of the source and target domains. Moreover, the availability of multiple modalities (i.e., images, questions and answers) in VQA poses further challenges in modeling the transferability between various modalities. In this paper, we address the above issues by proposing a novel supervised multi-modal domain adaptation method for VQA to learn joint feature embeddings across different domains and modalities. Specifically, we align the data distributions of the source and target domains by considering those modalities both jointly and separately. Extensive experiments on the benchmark VQA 2.0 and VizWiz datasets demonstrate that our proposed method outperforms the existing state-of-the-art baselines for open-ended VQA in this challenging domain adaptation setting."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2020-open">
<titleInfo>
<title>Open-Ended Visual Question Answering by Multi-Modal Domain Adaptation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yiming</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lin</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongwei</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lixin</namePart>
<namePart type="family">Duan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiebo</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We study the problem of visual question answering (VQA) in images by exploiting supervised domain adaptation, where there is a large amount of labeled data in the source domain but only limited labeled data in the target domain, with the goal to train a good target model. A straightforward solution is to fine-tune a pre-trained source model by using those limited labeled target data, but it usually cannot work well due to the considerable difference between the data distributions of the source and target domains. Moreover, the availability of multiple modalities (i.e., images, questions and answers) in VQA poses further challenges in modeling the transferability between various modalities. In this paper, we address the above issues by proposing a novel supervised multi-modal domain adaptation method for VQA to learn joint feature embeddings across different domains and modalities. Specifically, we align the data distributions of the source and target domains by considering those modalities both jointly and separately. Extensive experiments on the benchmark VQA 2.0 and VizWiz datasets demonstrate that our proposed method outperforms the existing state-of-the-art baselines for open-ended VQA in this challenging domain adaptation setting.</abstract>
<identifier type="citekey">xu-etal-2020-open</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.34</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.34/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>367</start>
<end>376</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Open-Ended Visual Question Answering by Multi-Modal Domain Adaptation
%A Xu, Yiming
%A Chen, Lin
%A Cheng, Zhongwei
%A Duan, Lixin
%A Luo, Jiebo
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F xu-etal-2020-open
%X We study the problem of visual question answering (VQA) in images by exploiting supervised domain adaptation, where there is a large amount of labeled data in the source domain but only limited labeled data in the target domain, with the goal to train a good target model. A straightforward solution is to fine-tune a pre-trained source model by using those limited labeled target data, but it usually cannot work well due to the considerable difference between the data distributions of the source and target domains. Moreover, the availability of multiple modalities (i.e., images, questions and answers) in VQA poses further challenges in modeling the transferability between various modalities. In this paper, we address the above issues by proposing a novel supervised multi-modal domain adaptation method for VQA to learn joint feature embeddings across different domains and modalities. Specifically, we align the data distributions of the source and target domains by considering those modalities both jointly and separately. Extensive experiments on the benchmark VQA 2.0 and VizWiz datasets demonstrate that our proposed method outperforms the existing state-of-the-art baselines for open-ended VQA in this challenging domain adaptation setting.
%R 10.18653/v1/2020.findings-emnlp.34
%U https://aclanthology.org/2020.findings-emnlp.34/
%U https://doi.org/10.18653/v1/2020.findings-emnlp.34
%P 367-376
Markdown (Informal)
[Open-Ended Visual Question Answering by Multi-Modal Domain Adaptation](https://aclanthology.org/2020.findings-emnlp.34/) (Xu et al., Findings 2020)
ACL