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 View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 13 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 13 samples from 1 repository, 10 ran (10 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-25 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

Cuberick-Orion/CIRPLANT officialmentioned on GitHubpytorchMITSyntology: 13 samples, 10 ran (0 instrument-failed) · 3 unverified report
Cuberick-Orion/CIRR officialmentioned on GitHubMITSyntology: not harvested report
naver/artemis mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested 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: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

10ran
3unverified

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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

Cuberick-Orion/CIRPLANT official repository 13 samples, 10 ran (0 instrument-failed) · 3 unverified
args_formatted_to_file _trainval_base.py ran MIT (permissive) · 2241b22aac3dc66f · report fixture: signature args:dict/0/?, ignore_empty:bool/0/bool, sorted_:bool/0/bool, multiline:bool/0/bool · returned str · level recorded 2026-09-26
batched_index_select in 44 papers model/utils/utils.py ran MIT (permissive) · dd1daced3a380bf9 · report fixture: signature input:Tensor/4/float, dim:int/0/int, index:Tensor/4/int · returned Tensor · level recorded 2026-09-25
instance_bce_with_logits in 7 papers model/OSCAR/modeling/modeling_bert.py ran MIT (permissive) · 5a4d93d8be97ccd9 · report fixture: signature logits:Tensor/2/float, labels:Tensor/2/float, reduction:str/0/str · returned Tensor · level recorded 2026-09-25
load_folder in 9 papers model/utils/utils.py ran MIT (permissive) · 6ebb002290340830 · report fixture: signature folder:str/0/str, suffix:str/0/str · returned list · level recorded 2026-09-25
load_wordforms model/OSCAR/utils/cbs.py ran MIT (permissive) · 9ae9f4ec47eca173 · report fixture: signature wordforms_tsvpath:str/0/str · returned dict · level recorded 2026-09-26
pairwise_cossim model/OSCAR/torch_functions.py ran fingerprinted MIT (permissive) · fe97aee1e09f00f2 · report fixture: signature x:Tensor/2/float, y:NoneType/0/? · returned Tensor · level recorded 2026-09-25
pairwise_distances in 34 papers
census: 14 implementations from 13 papers, 7 distinct outputs across 2 buckets, one shared input per bucket
model/OSCAR/torch_functions.py ran fingerprinted MIT (permissive) · 66d5486f0c42398d · report fixture: signature x:Tensor/2/float, y:Tensor/2/float · returned Tensor · level recorded 2026-09-25
select_best_beam_with_constraints model/OSCAR/utils/cbs.py ran MIT (permissive) · 513a7d2ac738d21f · report fixture: signature beams:Tensor/4/int, beam_log_probabilities:Tensor/3/float, given_constraints:Tensor/1/int, min_constraints_to_satisfy:int/0/int · returned tuple · level recorded 2026-09-25
setup_logger in 122 papers model/OSCAR/utils/logger.py ran MIT (permissive) · fc284dbe8d84606e · report fixture: signature name:str/0/str, save_dir:str/0/str, distributed_rank:int/0/int, filename:str/0/str · returned Logger · level recorded 2026-09-25
top_k_top_p_filtering in 96 papers
census: 8 implementations from 8 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
model/OSCAR/modeling/modeling_utils.py ran MIT (permissive) · 8164123ea94d7bb5 · report fixture: signature logits:Tensor/2/float, top_k:int/0/int, top_p:float/0/float, filter_value:float/0/float, min_tokens_to_keep:int/0/int · returned Tensor · level recorded 2026-09-25
create_model in 163 papers trainval_oscar.py unverified MIT (permissive) · f4cf22a5a6952c82 · report
evaluate_on_nocaps model/OSCAR/utils/caption_evaluate.py unverified MIT (permissive) · 0c36cf6fecae9668 · report
load_dataloader trainval_oscar.py unverified MIT (permissive) · 7703c53c246a68fa · 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