Papers › Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features

Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features

22 Aug 2023arXiv:2308.11485archive 2025-07-28

Alberto Baldrati, Marco Bertini, Tiberio Uricchio, Alberto del Bimbo

Given a query composed of a reference image and a relative caption, the Composed Image Retrieval goal is to retrieve images visually similar to the reference one that integrates the modifications expressed by the caption. Given that recent research has demonstrated the efficacy of large-scale vision and language pre-trained (VLP) models in various tasks, we rely on features from the OpenAI CLIP model to tackle the considered task. We initially perform a task-oriented fine-tuning of both CLIP encoders using the element-wise sum of visual and textual features. Then, in the second stage, we train a Combiner network that learns to combine the image-text features integrating the bimodal information and providing combined features used to perform the retrieval. We use contrastive learning in both stages of training. Starting from the bare CLIP features as a baseline, experimental results show that the task-oriented fine-tuning and the carefully crafted Combiner network are highly effective and outperform more complex state-of-the-art approaches on FashionIQ and CIRR, two popular and challenging datasets for composed image retrieval. Code and pre-trained models are available at https://github.com/ABaldrati/CLIP4Cir

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="2308.11485")

Code

Syntology Ran 4 of 5 code samples harvested from 2 repositories linked to this paper; 1 has no recorded run. Of those that ran: 4 ran with no contract checked.

By repository: official repository: 4 samples from 1 repository, 4 ran; community (archive-listed): 1 sample 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.

ABaldrati/CLIP4Cir officialmentioned in papermentioned on GitHubpytorchMIT report
chiangsonw/cala mentioned 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

5 samples harvested; 4 ran; 0 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.

4ran
1unverified

Licence: 0 of the 5 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

element_wise_sum ABaldrati/CLIP4Cir/src/utils.py official repository ran fingerprinted MIT (permissive) · c2601bfa66acc714 · report
generate_randomized_fiq_caption ABaldrati/CLIP4Cir/src/utils.py official repository ran MIT (permissive) · 17a33f0b1f407e2a · report
squarepad_transform ABaldrati/CLIP4Cir/src/data_utils.py official repository ran MIT (permissive) · a1580dd1883758f6 · report
targetpad_transform ABaldrati/CLIP4Cir/src/data_utils.py official repository ran MIT (permissive) · 9e2b18431cf6776f · report
extract_features_fusion_blip chiangsonw/cala/src/utils.py community (archive-listed) unverified MIT (permissive) · c7d305ae7ea0d9e0 · report

Tasks

Contrastive LearningImage RetrievalRetrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Retrieval CIRR CLIP4Cir (v3) (Recall@5+Recall_subset@1)/2 75.10 #12 of 17 Archive leaderboard report
Image Retrieval Fashion IQ CLIP4Cir (v3) (Recall@10+Recall@50)/2 55.36 #10 of 22 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

CLIPContrastive Learning

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