@inproceedings{qiao-etal-2025-hyden,
title = "{HYDEN}: Hyperbolic Density Representations for Medical Images and Reports",
author = "Qiao, Zhi and
Han, Linbin and
Zhen, Xiantong and
Gao, Jiahong and
Qian, Zhen",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.420/",
pages = "6285--6297",
abstract = "In light of the inherent entailment relations between images and text, embedding point vectors in hyperbolic space has been employed to leverage its hierarchical modeling advantages for visual semantic representation learning. However, point vector embeddings struggle to address semantic uncertainty, where an image may have multiple interpretations, and text may correspond to different images{---}a challenge especially prevalent in the medical domain. Therefor, we propose \textbf{HYDEN}, a novel hyperbolic density embedding based image-text representation learning approach tailored for specific medical domain data. This method integrates text-aware local features with global features from images, mapping image-text features to density features in hyperbolic space via using hyperbolic pseudo-Gaussian distributions. An encapsulation loss function is employed to model the partial order relations between image-text density distributions. Experimental results demonstrate the interpretability of our approach and its superior performance compared to the baseline methods across various zero-shot tasks and fine-tuning task on different datasets."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qiao-etal-2025-hyden">
<titleInfo>
<title>HYDEN: Hyperbolic Density Representations for Medical Images and Reports</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhi</namePart>
<namePart type="family">Qiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linbin</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiantong</namePart>
<namePart type="family">Zhen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiahong</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhen</namePart>
<namePart type="family">Qian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</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">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In light of the inherent entailment relations between images and text, embedding point vectors in hyperbolic space has been employed to leverage its hierarchical modeling advantages for visual semantic representation learning. However, point vector embeddings struggle to address semantic uncertainty, where an image may have multiple interpretations, and text may correspond to different images—a challenge especially prevalent in the medical domain. Therefor, we propose HYDEN, a novel hyperbolic density embedding based image-text representation learning approach tailored for specific medical domain data. This method integrates text-aware local features with global features from images, mapping image-text features to density features in hyperbolic space via using hyperbolic pseudo-Gaussian distributions. An encapsulation loss function is employed to model the partial order relations between image-text density distributions. Experimental results demonstrate the interpretability of our approach and its superior performance compared to the baseline methods across various zero-shot tasks and fine-tuning task on different datasets.</abstract>
<identifier type="citekey">qiao-etal-2025-hyden</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.420/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>6285</start>
<end>6297</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HYDEN: Hyperbolic Density Representations for Medical Images and Reports
%A Qiao, Zhi
%A Han, Linbin
%A Zhen, Xiantong
%A Gao, Jiahong
%A Qian, Zhen
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F qiao-etal-2025-hyden
%X In light of the inherent entailment relations between images and text, embedding point vectors in hyperbolic space has been employed to leverage its hierarchical modeling advantages for visual semantic representation learning. However, point vector embeddings struggle to address semantic uncertainty, where an image may have multiple interpretations, and text may correspond to different images—a challenge especially prevalent in the medical domain. Therefor, we propose HYDEN, a novel hyperbolic density embedding based image-text representation learning approach tailored for specific medical domain data. This method integrates text-aware local features with global features from images, mapping image-text features to density features in hyperbolic space via using hyperbolic pseudo-Gaussian distributions. An encapsulation loss function is employed to model the partial order relations between image-text density distributions. Experimental results demonstrate the interpretability of our approach and its superior performance compared to the baseline methods across various zero-shot tasks and fine-tuning task on different datasets.
%U https://aclanthology.org/2025.coling-main.420/
%P 6285-6297
Markdown (Informal)
[HYDEN: Hyperbolic Density Representations for Medical Images and Reports](https://aclanthology.org/2025.coling-main.420/) (Qiao et al., COLING 2025)
ACL