Instance-Level Composed Image Retrieval

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F25%3A00387491" target="_blank" >RIV/68407700:21230/25:00387491 - isvavai.cz</a>

Result on the web

<a href="https://openreview.net/pdf?id=7NEP4jGKwA" target="_blank" >https://openreview.net/pdf?id=7NEP4jGKwA</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Instance-Level Composed Image Retrieval

Original language description

The progress of composed image retrieval (CIR), a popular research direction in image retrieval, where a combined visual and textual query is used, is held back by the absence of high-quality training and evaluation data. We introduce a new evaluation dataset, i-CIR, which, unlike existing datasets, focuses on an instance- level class definition. The goal is to retrieve images that contain the same particular object as the visual query, presented under a variety of modifications defined by textual queries. Its design and curation process keep the dataset compact to facilitate future research, while maintaining its challenge—comparable to retrieval among more than 40M random distractors—through a semi-automated selection of hard negatives. To overcome the challenge of obtaining clean, diverse, and suitable training data, we leverage pre-trained vision-and-language models (VLMs) in a training-free approach called BASIC. The method separately estimates query-image- to-image and query-text-to-image similarities, performing late fusion to upweight images that satisfy both queries, while downweighting those that exhibit high similarity with only one of the two. Each individual similarity is further improved by a set of components that are simple and intuitive. BASIC sets a new state of the art on i-CIR but also on existing CIR datasets that follow a semantic-level class definition. Project page: https://vrg.fel.cvut.cz/icir/

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

Result was created during the realization of more than one project. More information in the Projects tab.

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Advances in Neural Information Processing Systems 38 (NeurIPS 2025)

ISBN

—

ISSN

1049-5258

e-ISSN

—

Number of pages

13

Pages from-to

—

Publisher name

Neural Information Processing Systems Foundation, Inc.

Place of publication

—

Event location

San Diego

Event date

Dec 2, 2025

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—