@inproceedings{wang-etal-2026-benchmarking-fine,
title = "Benchmarking the Fine-Grained Discriminability in Image-Text Retrieval via Controlled Contrastive Differences",
author = "Wang, Zhen and
Zhou, Xi and
Yang, Yating and
Ma, Bo and
Wang, Lei and
Dong, Rui and
Anwar, Azmat and
Miao, Siru",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1525/",
pages = "30491--30503",
ISBN = "979-8-89176-395-1",
abstract = "Existing cross-modal image-text retrieval models often retrieve samples with inconsistent details. To evaluate fine-grained discriminability, we introduce MSCOCO-CCD and Flickr30k-CCD, with three key features: (1) a two-level image content taxonomy for contrastive sample generation and fine-grained evaluation; (2) annotation of numerous contrastive samples, where each sample differs from the anchor by a controlled contrastive difference (CCD), with the specific type of difference labeled; (3) a fine-grained contrastive discrimination metric to assess the ability to distinguish fine-grained nuances. Extensive experiments demonstrate that contrastive samples can significantly degrade retrieval performance. Furthermore, fine-grained evaluation reveals that current models still struggle to effectively produce discriminative representations on certain feature types, such as entity emotion and scene attribute. Our datasets and related codes will be publicly released."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-benchmarking-fine">
<titleInfo>
<title>Benchmarking the Fine-Grained Discriminability in Image-Text Retrieval via Controlled Contrastive Differences</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yating</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Azmat</namePart>
<namePart type="family">Anwar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siru</namePart>
<namePart type="family">Miao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Existing cross-modal image-text retrieval models often retrieve samples with inconsistent details. To evaluate fine-grained discriminability, we introduce MSCOCO-CCD and Flickr30k-CCD, with three key features: (1) a two-level image content taxonomy for contrastive sample generation and fine-grained evaluation; (2) annotation of numerous contrastive samples, where each sample differs from the anchor by a controlled contrastive difference (CCD), with the specific type of difference labeled; (3) a fine-grained contrastive discrimination metric to assess the ability to distinguish fine-grained nuances. Extensive experiments demonstrate that contrastive samples can significantly degrade retrieval performance. Furthermore, fine-grained evaluation reveals that current models still struggle to effectively produce discriminative representations on certain feature types, such as entity emotion and scene attribute. Our datasets and related codes will be publicly released.</abstract>
<identifier type="citekey">wang-etal-2026-benchmarking-fine</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1525/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>30491</start>
<end>30503</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Benchmarking the Fine-Grained Discriminability in Image-Text Retrieval via Controlled Contrastive Differences
%A Wang, Zhen
%A Zhou, Xi
%A Yang, Yating
%A Ma, Bo
%A Wang, Lei
%A Dong, Rui
%A Anwar, Azmat
%A Miao, Siru
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F wang-etal-2026-benchmarking-fine
%X Existing cross-modal image-text retrieval models often retrieve samples with inconsistent details. To evaluate fine-grained discriminability, we introduce MSCOCO-CCD and Flickr30k-CCD, with three key features: (1) a two-level image content taxonomy for contrastive sample generation and fine-grained evaluation; (2) annotation of numerous contrastive samples, where each sample differs from the anchor by a controlled contrastive difference (CCD), with the specific type of difference labeled; (3) a fine-grained contrastive discrimination metric to assess the ability to distinguish fine-grained nuances. Extensive experiments demonstrate that contrastive samples can significantly degrade retrieval performance. Furthermore, fine-grained evaluation reveals that current models still struggle to effectively produce discriminative representations on certain feature types, such as entity emotion and scene attribute. Our datasets and related codes will be publicly released.
%U https://aclanthology.org/2026.findings-acl.1525/
%P 30491-30503
Markdown (Informal)
[Benchmarking the Fine-Grained Discriminability in Image-Text Retrieval via Controlled Contrastive Differences](https://aclanthology.org/2026.findings-acl.1525/) (Wang et al., Findings 2026)
ACL
- Zhen Wang, Xi Zhou, Yating Yang, Bo Ma, Lei Wang, Rui Dong, Azmat Anwar, and Siru Miao. 2026. Benchmarking the Fine-Grained Discriminability in Image-Text Retrieval via Controlled Contrastive Differences. In Findings of the Association for Computational Linguistics: ACL 2026, pages 30491–30503, San Diego, California, United States. Association for Computational Linguistics.