Papers › Bi-directional Training for Composed Image Retrieval via Text Prompt Learning

Bi-directional Training for Composed Image Retrieval via Text Prompt Learning

29 Mar 2023arXiv:2303.16604archive 2025-07-28

Zheyuan Liu, Weixuan Sun, Yicong Hong, Damien Teney, Stephen Gould

Composed image retrieval searches for a target image based on a multi-modal user query comprised of a reference image and modification text describing the desired changes. Existing approaches to solving this challenging task learn a mapping from the (reference image, modification text)-pair to an image embedding that is then matched against a large image corpus. One area that has not yet been explored is the reverse direction, which asks the question, what reference image when modified as described by the text would produce the given target image? In this work we propose a bi-directional training scheme that leverages such reversed queries and can be applied to existing composed image retrieval architectures with minimum changes, which improves the performance of the model. To encode the bi-directional query we prepend a learnable token to the modification text that designates the direction of the query and then finetune the parameters of the text embedding module. We make no other changes to the network architecture. Experiments on two standard datasets show that our novel approach achieves improved performance over a baseline BLIP-based model that itself already achieves competitive performance. Our code is released at https://github.com/Cuberick-Orion/Bi-Blip4CIR.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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

Cuberick-Orion/Bi-Blip4CIR officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder (arXiv:2305.16304; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Composed Image Retrieval (CoIR)Image RetrievalPrompt LearningRetrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Retrieval CIRR BLIP4CIR+Bi (Recall@5+Recall_subset@1)/2 72.59 #13 of 17 Archive leaderboard report
Image Retrieval CIRR BLIP4CIR+Bi Recall@10 83.88 #13 of 17 Archive leaderboard report
Image Retrieval Fashion IQ BLIP4CIR+Bi (Recall@10+Recall@50)/2 55.4 #9 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.

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