Papers › Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models

Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models

9 Aug 2021ICCV 2021 10arXiv:2108.04024archive 2025-07-28

Zheyuan Liu, Cristian Rodriguez-Opazo, Damien Teney, Stephen Gould

We extend the task of composed image retrieval, where an input query consists of an image and short textual description of how to modify the image. Existing methods have only been applied to non-complex images within narrow domains, such as fashion products, thereby limiting the scope of study on in-depth visual reasoning in rich image and language contexts. To address this issue, we collect the Compose Image Retrieval on Real-life images (CIRR) dataset, which consists of over 36,000 pairs of crowd-sourced, open-domain images with human-generated modifying text. To extend current methods to the open-domain, we propose CIRPLANT, a transformer based model that leverages rich pre-trained vision-and-language (V&L) knowledge for modifying visual features conditioned on natural language. Retrieval is then done by nearest neighbor lookup on the modified features. We demonstrate that with a relatively simple architecture, CIRPLANT outperforms existing methods on open-domain images, while matching state-of-the-art accuracy on the existing narrow datasets, such as fashion. Together with the release of CIRR, we believe this work will inspire further research on composed image retrieval.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2108.04024")

Code

Syntology Ran 0 of 13 code samples harvested from 1 repository linked to this paper; 13 have no recorded run.

By repository: official repository: 13 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Cuberick-Orion/CIRPLANT officialmentioned on GitHubpytorchMIT report
Cuberick-Orion/CIRR officialmentioned on GitHubMIT report
naver/artemis mentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

13 samples harvested; 0 ran; 0 honoured the contract we drafted; 13 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

13unverified

Licence: 0 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from Cuberick-Orion/CIRPLANT. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

args_formatted_to_file Cuberick-Orion/CIRPLANT/_trainval_base.py official repository unverified MIT (permissive) · 2241b22aac3dc66f · report
batched_index_select Cuberick-Orion/CIRPLANT/model/utils/utils.py official repository unverified MIT (permissive) · dd1daced3a380bf9 · report
create_model Cuberick-Orion/CIRPLANT/trainval_oscar.py official repository unverified MIT (permissive) · f4cf22a5a6952c82 · report
evaluate_on_nocaps Cuberick-Orion/CIRPLANT/model/OSCAR/utils/caption_evaluate.py official repository unverified MIT (permissive) · 0c36cf6fecae9668 · report
instance_bce_with_logits Cuberick-Orion/CIRPLANT/model/OSCAR/modeling/modeling_bert.py official repository unverified MIT (permissive) · 5a4d93d8be97ccd9 · report
load_dataloader Cuberick-Orion/CIRPLANT/trainval_oscar.py official repository unverified MIT (permissive) · 7703c53c246a68fa · report
load_folder Cuberick-Orion/CIRPLANT/model/utils/utils.py official repository unverified MIT (permissive) · 6ebb002290340830 · report
load_wordforms Cuberick-Orion/CIRPLANT/model/OSCAR/utils/cbs.py official repository unverified MIT (permissive) · 9ae9f4ec47eca173 · report
pairwise_cossim Cuberick-Orion/CIRPLANT/model/OSCAR/torch_functions.py official repository unverified MIT (permissive) · fe97aee1e09f00f2 · report
pairwise_distances Cuberick-Orion/CIRPLANT/model/OSCAR/torch_functions.py official repository unverified MIT (permissive) · 66d5486f0c42398d · report
select_best_beam_with_constraints Cuberick-Orion/CIRPLANT/model/OSCAR/utils/cbs.py official repository unverified MIT (permissive) · 513a7d2ac738d21f · report
setup_logger Cuberick-Orion/CIRPLANT/model/OSCAR/utils/logger.py official repository unverified MIT (permissive) · fc284dbe8d84606e · report
top_k_top_p_filtering Cuberick-Orion/CIRPLANT/model/OSCAR/modeling/modeling_utils.py official repository unverified MIT (permissive) · 8164123ea94d7bb5 · report

Tasks

Composed Image Retrieval (CoIR)Image RetrievalRetrievalVisual Reasoning

Datasets

Introduced by this paper, per the archive.

CIRR

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Retrieval CIRR CIRPLANT (Recall@5+Recall_subset@1)/2 45.88 #16 of 17 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections