@inproceedings{guo-etal-2022-clip4idc,
title = "{CLIP}4{IDC}: {CLIP} for Image Difference Captioning",
author = "Guo, Zixin and
Wang, Tzu-Jui and
Laaksonen, Jorma",
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
booktitle = "Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.aacl-short.5/",
doi = "10.18653/v1/2022.aacl-short.5",
pages = "33--42",
abstract = "Image Difference Captioning (IDC) aims at generating sentences to describe differences between two similar-looking images. Conventional approaches learn an IDC model with a pre-trained and usually frozen visual feature extractor. Accordingly, two major issues may arise: (1) a large domain gap usually exists between the pre-training datasets used for training such a visual encoder and that of the downstream IDC task, and (2) the visual feature extractor, when separately encoding two images, often does not effectively encode the visual changes between two images. Due to the excellent zero-shot performance of the recently proposed CLIP, we thus propose CLIP4IDC to transfer a CLIP model for the IDC task to address those issues. Different from directly fine-tuning CLIP to generate sentences, we introduce an adaptation training process to adapt CLIP`s visual encoder to capture and align differences in image pairs based on the textual descriptions. Experiments on three IDC benchmark datasets, CLEVR-Change, Spot-the-Diff, and Image-Editing-Request, demonstrate the effectiveness of CLIP4IDC."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2022-clip4idc">
<titleInfo>
<title>CLIP4IDC: CLIP for Image Difference Captioning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zixin</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tzu-Jui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorma</namePart>
<namePart type="family">Laaksonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
</titleInfo>
<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">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</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>
<name type="personal">
<namePart type="given">Chua-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Image Difference Captioning (IDC) aims at generating sentences to describe differences between two similar-looking images. Conventional approaches learn an IDC model with a pre-trained and usually frozen visual feature extractor. Accordingly, two major issues may arise: (1) a large domain gap usually exists between the pre-training datasets used for training such a visual encoder and that of the downstream IDC task, and (2) the visual feature extractor, when separately encoding two images, often does not effectively encode the visual changes between two images. Due to the excellent zero-shot performance of the recently proposed CLIP, we thus propose CLIP4IDC to transfer a CLIP model for the IDC task to address those issues. Different from directly fine-tuning CLIP to generate sentences, we introduce an adaptation training process to adapt CLIP‘s visual encoder to capture and align differences in image pairs based on the textual descriptions. Experiments on three IDC benchmark datasets, CLEVR-Change, Spot-the-Diff, and Image-Editing-Request, demonstrate the effectiveness of CLIP4IDC.</abstract>
<identifier type="citekey">guo-etal-2022-clip4idc</identifier>
<identifier type="doi">10.18653/v1/2022.aacl-short.5</identifier>
<location>
<url>https://aclanthology.org/2022.aacl-short.5/</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>33</start>
<end>42</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CLIP4IDC: CLIP for Image Difference Captioning
%A Guo, Zixin
%A Wang, Tzu-Jui
%A Laaksonen, Jorma
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%S Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F guo-etal-2022-clip4idc
%X Image Difference Captioning (IDC) aims at generating sentences to describe differences between two similar-looking images. Conventional approaches learn an IDC model with a pre-trained and usually frozen visual feature extractor. Accordingly, two major issues may arise: (1) a large domain gap usually exists between the pre-training datasets used for training such a visual encoder and that of the downstream IDC task, and (2) the visual feature extractor, when separately encoding two images, often does not effectively encode the visual changes between two images. Due to the excellent zero-shot performance of the recently proposed CLIP, we thus propose CLIP4IDC to transfer a CLIP model for the IDC task to address those issues. Different from directly fine-tuning CLIP to generate sentences, we introduce an adaptation training process to adapt CLIP‘s visual encoder to capture and align differences in image pairs based on the textual descriptions. Experiments on three IDC benchmark datasets, CLEVR-Change, Spot-the-Diff, and Image-Editing-Request, demonstrate the effectiveness of CLIP4IDC.
%R 10.18653/v1/2022.aacl-short.5
%U https://aclanthology.org/2022.aacl-short.5/
%U https://doi.org/10.18653/v1/2022.aacl-short.5
%P 33-42
Markdown (Informal)
[CLIP4IDC: CLIP for Image Difference Captioning](https://aclanthology.org/2022.aacl-short.5/) (Guo et al., AACL-IJCNLP 2022)
ACL
- Zixin Guo, Tzu-Jui Wang, and Jorma Laaksonen. 2022. CLIP4IDC: CLIP for Image Difference Captioning. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 33–42, Online only. Association for Computational Linguistics.