@inproceedings{jiang-etal-2024-infrared,
title = "Infrared-{LL}a{VA}: Enhancing Understanding of Infrared Images in Multi-Modal Large Language Models",
author = "Jiang, Shixin and
Chen, Zerui and
Liang, Jiafeng and
Zhao, Yanyan and
Liu, Ming and
Qin, Bing",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.501",
pages = "8573--8591",
abstract = "Expanding the understanding capabilities of multi-modal large language models (MLLMs) for infrared modality is a challenge due to the single-modality nature and limited amount of training data. Existing methods typically construct a uniform embedding space for cross-modal alignment and leverage abundant visual image data to indirectly understand infrared images. However, they ignore the supervisory signals of infrared-modality-specific attributes, which may lead to biased understanding of infrared images. To address this issue, we propose a debating multi-agent generation system which transfers knowledge from visible images to generate infrared image-text pairs and infrared instruction data. Moreover, we construct an infrared question-answering benchmark based on common infrared tasks. Experimental results from incremental fine-tuning on existing models and our Infrared-LLaVA-7B trained from scratch on infrared data demonstrate the effectiveness of the generated data and the feasibility of the generation approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-etal-2024-infrared">
<titleInfo>
<title>Infrared-LLaVA: Enhancing Understanding of Infrared Images in Multi-Modal Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shixin</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zerui</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiafeng</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanyan</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Expanding the understanding capabilities of multi-modal large language models (MLLMs) for infrared modality is a challenge due to the single-modality nature and limited amount of training data. Existing methods typically construct a uniform embedding space for cross-modal alignment and leverage abundant visual image data to indirectly understand infrared images. However, they ignore the supervisory signals of infrared-modality-specific attributes, which may lead to biased understanding of infrared images. To address this issue, we propose a debating multi-agent generation system which transfers knowledge from visible images to generate infrared image-text pairs and infrared instruction data. Moreover, we construct an infrared question-answering benchmark based on common infrared tasks. Experimental results from incremental fine-tuning on existing models and our Infrared-LLaVA-7B trained from scratch on infrared data demonstrate the effectiveness of the generated data and the feasibility of the generation approach.</abstract>
<identifier type="citekey">jiang-etal-2024-infrared</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.501</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>8573</start>
<end>8591</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Infrared-LLaVA: Enhancing Understanding of Infrared Images in Multi-Modal Large Language Models
%A Jiang, Shixin
%A Chen, Zerui
%A Liang, Jiafeng
%A Zhao, Yanyan
%A Liu, Ming
%A Qin, Bing
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F jiang-etal-2024-infrared
%X Expanding the understanding capabilities of multi-modal large language models (MLLMs) for infrared modality is a challenge due to the single-modality nature and limited amount of training data. Existing methods typically construct a uniform embedding space for cross-modal alignment and leverage abundant visual image data to indirectly understand infrared images. However, they ignore the supervisory signals of infrared-modality-specific attributes, which may lead to biased understanding of infrared images. To address this issue, we propose a debating multi-agent generation system which transfers knowledge from visible images to generate infrared image-text pairs and infrared instruction data. Moreover, we construct an infrared question-answering benchmark based on common infrared tasks. Experimental results from incremental fine-tuning on existing models and our Infrared-LLaVA-7B trained from scratch on infrared data demonstrate the effectiveness of the generated data and the feasibility of the generation approach.
%U https://aclanthology.org/2024.findings-emnlp.501
%P 8573-8591
Markdown (Informal)
[Infrared-LLaVA: Enhancing Understanding of Infrared Images in Multi-Modal Large Language Models](https://aclanthology.org/2024.findings-emnlp.501) (Jiang et al., Findings 2024)
ACL