@inproceedings{wen-etal-2022-visual,
title = "Visual Prompt Tuning for Few-Shot Text Classification",
author = "Wen, Jingyuan and
Luo, Yutian and
Fei, Nanyi and
Yang, Guoxing and
Lu, Zhiwu and
Jiang, Hao and
Jiang, Jie and
Cao, Zhao",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.492",
pages = "5560--5570",
abstract = "Deploying large-scale pre-trained models in the prompt-tuning paradigm has demonstrated promising performance in few-shot learning. Particularly, vision-language pre-training models (VL-PTMs) have been intensively explored in various few-shot downstream tasks. However, most existing works only apply VL-PTMs to visual tasks like image classification, with few attempts being made on language tasks like text classification. In few-shot text classification, a feasible paradigm for deploying VL-PTMs is to align the input samples and their category names via the text encoders. However, it leads to the waste of visual information learned by the image encoders of VL-PTMs. To overcome this drawback, we propose a novel method named Visual Prompt Tuning (VPT). To our best knowledge, this method is the first attempt to deploy VL-PTM in few-shot text classification task. The main idea is to generate the image embeddings w.r.t. category names as visual prompt and then add them to the aligning process. Extensive experiments show that our VPT can achieve significant improvements under both zero-shot and few-shot settings. Importantly, our VPT even outperforms the most recent prompt-tuning methods on five public text classification datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wen-etal-2022-visual">
<titleInfo>
<title>Visual Prompt Tuning for Few-Shot Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jingyuan</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yutian</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nanyi</namePart>
<namePart type="family">Fei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guoxing</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiwu</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhao</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Deploying large-scale pre-trained models in the prompt-tuning paradigm has demonstrated promising performance in few-shot learning. Particularly, vision-language pre-training models (VL-PTMs) have been intensively explored in various few-shot downstream tasks. However, most existing works only apply VL-PTMs to visual tasks like image classification, with few attempts being made on language tasks like text classification. In few-shot text classification, a feasible paradigm for deploying VL-PTMs is to align the input samples and their category names via the text encoders. However, it leads to the waste of visual information learned by the image encoders of VL-PTMs. To overcome this drawback, we propose a novel method named Visual Prompt Tuning (VPT). To our best knowledge, this method is the first attempt to deploy VL-PTM in few-shot text classification task. The main idea is to generate the image embeddings w.r.t. category names as visual prompt and then add them to the aligning process. Extensive experiments show that our VPT can achieve significant improvements under both zero-shot and few-shot settings. Importantly, our VPT even outperforms the most recent prompt-tuning methods on five public text classification datasets.</abstract>
<identifier type="citekey">wen-etal-2022-visual</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.492</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>5560</start>
<end>5570</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Visual Prompt Tuning for Few-Shot Text Classification
%A Wen, Jingyuan
%A Luo, Yutian
%A Fei, Nanyi
%A Yang, Guoxing
%A Lu, Zhiwu
%A Jiang, Hao
%A Jiang, Jie
%A Cao, Zhao
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F wen-etal-2022-visual
%X Deploying large-scale pre-trained models in the prompt-tuning paradigm has demonstrated promising performance in few-shot learning. Particularly, vision-language pre-training models (VL-PTMs) have been intensively explored in various few-shot downstream tasks. However, most existing works only apply VL-PTMs to visual tasks like image classification, with few attempts being made on language tasks like text classification. In few-shot text classification, a feasible paradigm for deploying VL-PTMs is to align the input samples and their category names via the text encoders. However, it leads to the waste of visual information learned by the image encoders of VL-PTMs. To overcome this drawback, we propose a novel method named Visual Prompt Tuning (VPT). To our best knowledge, this method is the first attempt to deploy VL-PTM in few-shot text classification task. The main idea is to generate the image embeddings w.r.t. category names as visual prompt and then add them to the aligning process. Extensive experiments show that our VPT can achieve significant improvements under both zero-shot and few-shot settings. Importantly, our VPT even outperforms the most recent prompt-tuning methods on five public text classification datasets.
%U https://aclanthology.org/2022.coling-1.492
%P 5560-5570
Markdown (Informal)
[Visual Prompt Tuning for Few-Shot Text Classification](https://aclanthology.org/2022.coling-1.492) (Wen et al., COLING 2022)
ACL
- Jingyuan Wen, Yutian Luo, Nanyi Fei, Guoxing Yang, Zhiwu Lu, Hao Jiang, Jie Jiang, and Zhao Cao. 2022. Visual Prompt Tuning for Few-Shot Text Classification. In Proceedings of the 29th International Conference on Computational Linguistics, pages 5560–5570, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.