Papers › Effective Conditioned and Composed Image Retrieval Combining CLIP-Based Features

Effective Conditioned and Composed Image Retrieval Combining CLIP-Based Features

1 Jan 2022CVPR 2022 1archive 2025-07-28

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

Conditioned and composed image retrieval extend CBIR systems by combining a query image with an additional text that expresses the intent of the user, describing additional requests w.r.t. the visual content of the query image. This type of search is interesting for e-commerce applications, e.g. to develop interactive multimodal searches and chatbots. In this demo, we present an interactive system based on a combiner network, trained using contrastive learning, that combines visual and textual features obtained from the OpenAI CLIP network to address conditioned CBIR. The system can be used to improve e-shop search engines. For example, considering the fashion domain it lets users search for dresses, shirts and toptees using a candidate start image and expressing some visual differences w.r.t. its visual content, e.g. asking to change color, pattern or shape. The proposed network obtains state-of-the-art performance on the FashionIQ dataset and on the more recent CIRR dataset, showing its applicability to the fashion domain for conditioned retrieval, and to more generic content considering the more general task of composed image retrieval.

PaperPDFCode

Code

ABaldrati/CLIP4Cir officialpytorchMIT report
abaldrati/clip4cirdemo mentioned in paperpytorch 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

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

Tasks

Composed Image Retrieval (CoIR)Contrastive LearningImage RetrievalRetrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Retrieval CIRR CLIP4Cir (Recall@5+Recall_subset@1)/2 63.87 #15 of 17 Archive leaderboard report
Image Retrieval Fashion IQ CLIP4Cir (Recall@10+Recall@50)/2 47.21 #16 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

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