@inproceedings{lee-etal-2021-umic,
title = "{UMIC}: An Unreferenced Metric for Image Captioning via Contrastive Learning",
author = "Lee, Hwanhee and
Yoon, Seunghyun and
Dernoncourt, Franck and
Bui, Trung and
Jung, Kyomin",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-short.29",
doi = "10.18653/v1/2021.acl-short.29",
pages = "220--226",
abstract = "Despite the success of various text generation metrics such as BERTScore, it is still difficult to evaluate the image captions without enough reference captions due to the diversity of the descriptions. In this paper, we introduce a new metric UMIC, an Unreferenced Metric for Image Captioning which does not require reference captions to evaluate image captions. Based on Vision-and-Language BERT, we train UMIC to discriminate negative captions via contrastive learning. Also, we observe critical problems of the previous benchmark dataset (i.e., human annotations) on image captioning metric, and introduce a new collection of human annotations on the generated captions. We validate UMIC on four datasets, including our new dataset, and show that UMIC has a higher correlation than all previous metrics that require multiple references.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2021-umic">
<titleInfo>
<title>UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hwanhee</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seunghyun</namePart>
<namePart type="family">Yoon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Franck</namePart>
<namePart type="family">Dernoncourt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trung</namePart>
<namePart type="family">Bui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyomin</namePart>
<namePart type="family">Jung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</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>Despite the success of various text generation metrics such as BERTScore, it is still difficult to evaluate the image captions without enough reference captions due to the diversity of the descriptions. In this paper, we introduce a new metric UMIC, an Unreferenced Metric for Image Captioning which does not require reference captions to evaluate image captions. Based on Vision-and-Language BERT, we train UMIC to discriminate negative captions via contrastive learning. Also, we observe critical problems of the previous benchmark dataset (i.e., human annotations) on image captioning metric, and introduce a new collection of human annotations on the generated captions. We validate UMIC on four datasets, including our new dataset, and show that UMIC has a higher correlation than all previous metrics that require multiple references.</abstract>
<identifier type="citekey">lee-etal-2021-umic</identifier>
<identifier type="doi">10.18653/v1/2021.acl-short.29</identifier>
<location>
<url>https://aclanthology.org/2021.acl-short.29</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>220</start>
<end>226</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning
%A Lee, Hwanhee
%A Yoon, Seunghyun
%A Dernoncourt, Franck
%A Bui, Trung
%A Jung, Kyomin
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F lee-etal-2021-umic
%X Despite the success of various text generation metrics such as BERTScore, it is still difficult to evaluate the image captions without enough reference captions due to the diversity of the descriptions. In this paper, we introduce a new metric UMIC, an Unreferenced Metric for Image Captioning which does not require reference captions to evaluate image captions. Based on Vision-and-Language BERT, we train UMIC to discriminate negative captions via contrastive learning. Also, we observe critical problems of the previous benchmark dataset (i.e., human annotations) on image captioning metric, and introduce a new collection of human annotations on the generated captions. We validate UMIC on four datasets, including our new dataset, and show that UMIC has a higher correlation than all previous metrics that require multiple references.
%R 10.18653/v1/2021.acl-short.29
%U https://aclanthology.org/2021.acl-short.29
%U https://doi.org/10.18653/v1/2021.acl-short.29
%P 220-226
Markdown (Informal)
[UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning](https://aclanthology.org/2021.acl-short.29) (Lee et al., ACL-IJCNLP 2021)
ACL
- Hwanhee Lee, Seunghyun Yoon, Franck Dernoncourt, Trung Bui, and Kyomin Jung. 2021. UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 220–226, Online. Association for Computational Linguistics.