Papers › Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity

Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity

7 Sep 2024arXiv:2409.04918archive 2025-07-28

Ren-Di Wu, Yu-Yen Lin, Huei-Fang Yang

Composed image retrieval (CIR), which formulates the query as a combination of a reference image and modified text, has emerged as a new form of image search due to its enhanced ability to capture user intent. However, training a CIR model in a supervised manner typically requires labor-intensive collection of (reference image, text modifier, target image) triplets. While existing zero-shot CIR (ZS-CIR) methods eliminate the need for training on specific downstream datasets, they still require additional pretraining on large-scale image datasets. In this paper, we introduce a training-free approach for ZS-CIR. Our approach, Weighted Modality fusion and similarity for CIR (WeiMoCIR), operates under the assumption that image and text modalities can be effectively combined using a simple weighted average. This allows the query representation to be constructed directly from the reference image and text modifier. To further enhance retrieval performance, we employ multimodal large language models (MLLMs) to generate image captions for the database images and incorporate these textual captions into the similarity computation by combining them with image information using a weighted average. Our approach is simple, easy to implement, and its effectiveness is validated through experiments on the FashionIQ and CIRR datasets. Code is available at https://github.com/whats2000/WeiMoCIR.

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="2409.04918")

Code

Syntology Ran 2 of 2 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 2 ran with no contract checked.

By repository: official repository: 2 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

whats2000/WeiMoCIR officialmentioned in papermentioned on GitHubpytorchMIT 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

2 samples harvested; 2 ran; 0 honoured the contract we drafted; 0 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.

2ran

Licence: 0 of the 2 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 whats2000/WeiMoCIR. “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.

squarepad_transform whats2000/WeiMoCIR/src/data_utils.py official repository ran MIT (permissive) · a1580dd1883758f6 · report
targetpad_transform whats2000/WeiMoCIR/src/data_utils.py official repository ran MIT (permissive) · 9e2b18431cf6776f · report

Tasks

Image CaptioningImage 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) CIRR WeiMoCIR (CLIP G/14) R@1 31.04 #12 of 47 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) CIRR WeiMoCIR (CLIP G/14) R@5 60.41 #12 of 47 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) CIRR WeiMoCIR (CLIP L/14) R@1 30.94 #13 of 47 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) CIRR WeiMoCIR (CLIP L/14) R@5 60.87 #13 of 47 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) CIRR WeiMoCIR (CLIP H/14) R@1 29.11 #18 of 47 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) CIRR WeiMoCIR (CLIP H/14) R@5 59.76 #18 of 47 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) CIRR WeiMoCIR (CLIP B/32) R@1 26.31 #19 of 47 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) CIRR WeiMoCIR (CLIP B/32) R@5 57.69 #19 of 47 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) Fashion IQ WeiMoCIR (CLIP G/14) (Recall@10+Recall@50)/2 47.16 #9 of 41 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) Fashion IQ WeiMoCIR (CLIP H/14) (Recall@10+Recall@50)/2 44.58 #15 of 41 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) Fashion IQ WeiMoCIR (CLIP L/14) (Recall@10+Recall@50)/2 41.27 #22 of 41 Archive leaderboard report
Zero-Shot Composed Image Retrieval (ZS-CIR) Fashion IQ WeiMoCIR (CLIP B/32) (Recall@10+Recall@50)/2 39.84 #24 of 41 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