Data Roaming and Quality Assessment for Composed Image Retrieval

Matan Levy*, Rami Ben-Ari, Nir Darshan, Dani Lischinski

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review


The task of Composed Image Retrieval (CoIR) involves queries that combine image and text modalities, allowing users to express their intent more effectively. However, current CoIR datasets are orders of magnitude smaller compared to other vision and language (V&L) datasets. Additionally, some of these datasets have noticeable issues, such as queries containing redundant modalities. To address these shortcomings, we introduce the Large Scale Composed Image Retrieval (LaSCo) dataset, a new CoIR dataset which is ten times larger than existing ones. Pre-training on our LaSCo, shows a noteworthy improvement in performance, even in zero-shot. Furthermore, we propose a new approach for analyzing CoIR datasets and methods, which detects modality redundancy or necessity, in queries. We also introduce a new CoIR baseline, the Cross-Attention driven Shift Encoder (CASE). This baseline allows for early fusion of modalities using a cross-attention module and employs an additional auxiliary task during training. Our experiments demonstrate that this new baseline outperforms the current state-of-the-art methods on established benchmarks like FashionIQ and CIRR.

Original languageAmerican English
Pages (from-to)2991-2999
Number of pages9
JournalProceedings of the AAAI Conference on Artificial Intelligence
Issue number4
StatePublished - 25 Mar 2024
Event38th AAAI Conference on Artificial Intelligence, AAAI 2024 - Vancouver, Canada
Duration: 20 Feb 202427 Feb 2024

Bibliographical note

Publisher Copyright:
Copyright © 2024, Association for the Advancement of Artificial Intelligence ( All rights reserved.


Dive into the research topics of 'Data Roaming and Quality Assessment for Composed Image Retrieval'. Together they form a unique fingerprint.

Cite this