Papers › iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval

iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval

5 May 2024arXiv:2405.02951archive 2025-07-28

Lorenzo Agnolucci, Alberto Baldrati, Marco Bertini, Alberto del Bimbo

Given a query consisting of a reference image and a relative caption, Composed Image Retrieval (CIR) aims to retrieve target images visually similar to the reference one while incorporating the changes specified in the relative caption. The reliance of supervised methods on labor-intensive manually labeled datasets hinders their broad applicability. In this work, we introduce a new task, Zero-Shot CIR (ZS-CIR), that addresses CIR without the need for a labeled training dataset. We propose an approach named iSEARLE (improved zero-Shot composEd imAge Retrieval with textuaL invErsion) that involves mapping the visual information of the reference image into a pseudo-word token in CLIP token embedding space and combining it with the relative caption. To foster research on ZS-CIR, we present an open-domain benchmarking dataset named CIRCO (Composed Image Retrieval on Common Objects in context), the first CIR dataset where each query is labeled with multiple ground truths and a semantic categorization. The experimental results illustrate that iSEARLE obtains state-of-the-art performance on three different CIR datasets -- FashionIQ, CIRR, and the proposed CIRCO -- and two additional evaluation settings, namely domain conversion and object composition. The dataset, the code, and the model are publicly available at https://github.com/miccunifi/SEARLE.

PaperPDFCodeCode 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="2405.02951")

Code

Syntology Ran 3 of 4 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran with no contract checked.

By repository: named in the paper: 4 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

miccunifi/circo officialmentioned on GitHubpytorchNOASSERTION report
miccunifi/searle mentioned in papermentioned 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

4 samples harvested; 3 ran; 1 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
2ran
1unverified

Licence: 4 of the 4 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 miccunifi/searle. “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.

collate_fn miccunifi/searle/src/data_utils.py named in the paper ran · honoured contract fingerprinted no licence file found · pointer only · b6c1f837e6faaeba · report
process_phrase miccunifi/searle/src/gpt_phrases_generation.py named in the paper ran fingerprinted licence not identified · pointer only · dc736d696fd0df44 · report
targetpad_transform miccunifi/searle/src/data_utils.py named in the paper ran licence not identified · pointer only · 9476d6cebb3ecfb9 · report
contrastive_loss miccunifi/searle/src/utils.py named in the paper unverified licence not identified · pointer only · f96edb7ca8fe54fe · report

Tasks

BenchmarkingComposed Image Retrieval (CoIR)Image RetrievalRetrievalZero-Shot Composed Image Retrieval (ZS-CIR)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Zero-Shot Composed Image Retrieval (ZS-CIR) CIRCO iSEARLE-XL (CLIP L/14) mAP@10 13.61 #32 of 43 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) CIRCO iSEARLE-XL-OTI (CLIP L/14) mAP@10 12.67 #36 of 43 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) CIRCO iSEARLE (CLIP B/32) mAP@10 11.24 #38 of 43 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) CIRCO iSEARLE-OTI (CLIP B/32) mAP@10 10.94 #39 of 43 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) CIRR iSEARLE (CLIP B/32) R@5 55.69 #34 of 47 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) CIRR iSEARLE-OTI (CLIP B/32) R@5 55.18 #36 of 47 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) CIRR iSEARLE-XL-OTI (CLIP L/14) R@5 54.05 #41 of 47 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) CIRR iSEARLE-XL (CLIP L/14) R@5 54.00 #42 of 47 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) COCO (Common Objects in Context) iSEARLE-XL-OTI (CLIP L/14) Actions Recall@5 32.55 #1 of 10 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) COCO (Common Objects in Context) iSEARLE-XL (CLIP L/14) Actions Recall@5 30.05 #3 of 10 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) COCO (Common Objects in Context) iSEARLE-OTI (CLIP B/32) Actions Recall@5 26.63 #6 of 10 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) COCO (Common Objects in Context) iSEARLE (CLIP B/32) Actions Recall@5 26.40 #7 of 10 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) Fashion IQ iSEARLE-XL-OTI (CLIP L/14) (Recall@10+Recall@50)/2 39.39 #26 of 41 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) Fashion IQ iSEARLE-XL (CLIP L/14) (Recall@10+Recall@50)/2 38.24 #30 of 41 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) Fashion IQ iSEARLE-OTI (CLIP B/32) (Recall@10+Recall@50)/2 34.93 #35 of 41 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) Fashion IQ iSEARLE (CLIP B/32) (Recall@10+Recall@50)/2 34.60 #36 of 41 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) ImageNet iSEARLE-XL (CLIP L/14) Average Recall 24.46 #1 of 11 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) ImageNet iSEARLE-XL-OTI (CLIP L/14) Average Recall 22.59 #2 of 11 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) ImageNet iSEARLE (CLIP B/32) Average Recall 16.01 #8 of 11 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) ImageNet iSEARLE-OTI (CLIP B/32) Average Recall 15.62 #9 of 11 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) ImageNet-R iSEARLE-XL (CLIP L/14) (Recall@10+Recall@50)/2 24.46 #5 of 20 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) ImageNet-R iSEARLE (CLIP B/32) (Recall@10+Recall@50)/2 16.01 #11 of 20 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) ImageNet-R iSEARLE-OTI (CLIP B/32) (Recall@10+Recall@50)/2 15.62 #12 of 20 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.

Methods

CLIP

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