@inproceedings{nishida-etal-2022-improving,
title = "Improving Few-Shot Image Classification Using Machine- and User-Generated Natural Language Descriptions",
author = "Nishida, Kosuke and
Nishida, Kyosuke and
Nishioka, Shuichi",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-naacl.106",
doi = "10.18653/v1/2022.findings-naacl.106",
pages = "1421--1430",
abstract = "Humans can obtain the knowledge of novel visual concepts from language descriptions, and we thus use the few-shot image classification task to investigate whether a machine learning model can have this capability. Our proposed model, LIDE (Learning from Image and DEscription), has a text decoder to generate the descriptions and a text encoder to obtain the text representations of machine- or user-generated descriptions. We confirmed that LIDE with machine-generated descriptions outperformed baseline models. Moreover, the performance was improved further with high-quality user-generated descriptions. The generated descriptions can be viewed as the explanations of the model{'}s predictions, and we observed that such explanations were consistent with prediction results. We also investigated why the language description improves the few-shot image classification performance by comparing the image representations and the text representations in the feature spaces.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nishida-etal-2022-improving">
<titleInfo>
<title>Improving Few-Shot Image Classification Using Machine- and User-Generated Natural Language Descriptions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kosuke</namePart>
<namePart type="family">Nishida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyosuke</namePart>
<namePart type="family">Nishida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuichi</namePart>
<namePart type="family">Nishioka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Humans can obtain the knowledge of novel visual concepts from language descriptions, and we thus use the few-shot image classification task to investigate whether a machine learning model can have this capability. Our proposed model, LIDE (Learning from Image and DEscription), has a text decoder to generate the descriptions and a text encoder to obtain the text representations of machine- or user-generated descriptions. We confirmed that LIDE with machine-generated descriptions outperformed baseline models. Moreover, the performance was improved further with high-quality user-generated descriptions. The generated descriptions can be viewed as the explanations of the model’s predictions, and we observed that such explanations were consistent with prediction results. We also investigated why the language description improves the few-shot image classification performance by comparing the image representations and the text representations in the feature spaces.</abstract>
<identifier type="citekey">nishida-etal-2022-improving</identifier>
<identifier type="doi">10.18653/v1/2022.findings-naacl.106</identifier>
<location>
<url>https://aclanthology.org/2022.findings-naacl.106</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1421</start>
<end>1430</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Few-Shot Image Classification Using Machine- and User-Generated Natural Language Descriptions
%A Nishida, Kosuke
%A Nishida, Kyosuke
%A Nishioka, Shuichi
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Findings of the Association for Computational Linguistics: NAACL 2022
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F nishida-etal-2022-improving
%X Humans can obtain the knowledge of novel visual concepts from language descriptions, and we thus use the few-shot image classification task to investigate whether a machine learning model can have this capability. Our proposed model, LIDE (Learning from Image and DEscription), has a text decoder to generate the descriptions and a text encoder to obtain the text representations of machine- or user-generated descriptions. We confirmed that LIDE with machine-generated descriptions outperformed baseline models. Moreover, the performance was improved further with high-quality user-generated descriptions. The generated descriptions can be viewed as the explanations of the model’s predictions, and we observed that such explanations were consistent with prediction results. We also investigated why the language description improves the few-shot image classification performance by comparing the image representations and the text representations in the feature spaces.
%R 10.18653/v1/2022.findings-naacl.106
%U https://aclanthology.org/2022.findings-naacl.106
%U https://doi.org/10.18653/v1/2022.findings-naacl.106
%P 1421-1430
Markdown (Informal)
[Improving Few-Shot Image Classification Using Machine- and User-Generated Natural Language Descriptions](https://aclanthology.org/2022.findings-naacl.106) (Nishida et al., Findings 2022)
ACL