@inproceedings{kim-etal-2019-image,
title = "Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approach",
author = "Kim, Dong-Jin and
Choi, Jinsoo and
Oh, Tae-Hyun and
Kweon, In So",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1208/",
doi = "10.18653/v1/D19-1208",
pages = "2012--2023",
abstract = "Constructing an organized dataset comprised of a large number of images and several captions for each image is a laborious task, which requires vast human effort. On the other hand, collecting a large number of images and sentences separately may be immensely easier. In this paper, we develop a novel data-efficient semi-supervised framework for training an image captioning model. We leverage massive unpaired image and caption data by learning to associate them. To this end, our proposed semi-supervised learning method assigns pseudo-labels to unpaired samples via Generative Adversarial Networks to learn the joint distribution of image and caption. To evaluate, we construct scarcely-paired COCO dataset, a modified version of MS COCO caption dataset. The empirical results show the effectiveness of our method compared to several strong baselines, especially when the amount of the paired samples are scarce."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2019-image">
<titleInfo>
<title>Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dong-Jin</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinsoo</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tae-Hyun</namePart>
<namePart type="family">Oh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">In</namePart>
<namePart type="given">So</namePart>
<namePart type="family">Kweon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Constructing an organized dataset comprised of a large number of images and several captions for each image is a laborious task, which requires vast human effort. On the other hand, collecting a large number of images and sentences separately may be immensely easier. In this paper, we develop a novel data-efficient semi-supervised framework for training an image captioning model. We leverage massive unpaired image and caption data by learning to associate them. To this end, our proposed semi-supervised learning method assigns pseudo-labels to unpaired samples via Generative Adversarial Networks to learn the joint distribution of image and caption. To evaluate, we construct scarcely-paired COCO dataset, a modified version of MS COCO caption dataset. The empirical results show the effectiveness of our method compared to several strong baselines, especially when the amount of the paired samples are scarce.</abstract>
<identifier type="citekey">kim-etal-2019-image</identifier>
<identifier type="doi">10.18653/v1/D19-1208</identifier>
<location>
<url>https://aclanthology.org/D19-1208/</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>2012</start>
<end>2023</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approach
%A Kim, Dong-Jin
%A Choi, Jinsoo
%A Oh, Tae-Hyun
%A Kweon, In So
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F kim-etal-2019-image
%X Constructing an organized dataset comprised of a large number of images and several captions for each image is a laborious task, which requires vast human effort. On the other hand, collecting a large number of images and sentences separately may be immensely easier. In this paper, we develop a novel data-efficient semi-supervised framework for training an image captioning model. We leverage massive unpaired image and caption data by learning to associate them. To this end, our proposed semi-supervised learning method assigns pseudo-labels to unpaired samples via Generative Adversarial Networks to learn the joint distribution of image and caption. To evaluate, we construct scarcely-paired COCO dataset, a modified version of MS COCO caption dataset. The empirical results show the effectiveness of our method compared to several strong baselines, especially when the amount of the paired samples are scarce.
%R 10.18653/v1/D19-1208
%U https://aclanthology.org/D19-1208/
%U https://doi.org/10.18653/v1/D19-1208
%P 2012-2023
Markdown (Informal)
[Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approach](https://aclanthology.org/D19-1208/) (Kim et al., EMNLP-IJCNLP 2019)
ACL