Zero-Shot Composed Image Retrieval (ZS-CIR)

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

12 leaderboard tables shown for this task, 12 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 12 until expanded.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

11 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

25 shown of 25 papers with code (36 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Semantic Editing Increment Benefits Zero-Shot Composed Image Retrieval
  28 Oct 2024 2 repositories listed
  To address this limitation, this paper proposes a training-free method called Semantic Editing Increment for ZS-CIR (SEIZE) to retrieve the target image based on the query image and text without training.
• LDRE: LLM-based Divergent Reasoning and Ensemble for Zero-Shot Composed Image Retrieval
  11 Jul 2024 2 repositories listed
  To conduct ZS-CIR, the prevailing methods employ pre-trained image-to-text models to transform the query image and text into a single text, which is then projected into the common feature space by CLIP to retrieve the…
• iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval
  5 May 2024 2 repositories listed Syntology ran 3 of 4 samples · 1 unverified · 4 pointer-only (licence)
  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…
• Zero-Shot Composed Image Retrieval with Textual Inversion
  27 Mar 2023 2 repositories listed
  Composed Image Retrieval (CIR) aims to retrieve a target image based on a query composed of a reference image and a relative caption that describes the difference between the two images.
• "This is my unicorn, Fluffy": Personalizing frozen vision-language representations
  4 Apr 2022 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  We propose an architecture for solving PerVL that operates by extending the input vocabulary of a pretrained model with new word embeddings for the new personalized concepts.
• CoLLM: A Large Language Model for Composed Image Retrieval
  25 Mar 2025 1 repository listed
  Experimental results demonstrate that CoLLM achieves state-of-the-art performance across multiple CIR benchmarks and settings.
• Missing Target-Relevant Information Prediction with World Model for Accurate Zero-Shot Composed Image Retrieval
  21 Mar 2025 1 repository listed
  The key challenge for ZS-CIR tasks is to modify a reference image according to manipulation text to accurately retrieve a target image, especially when the reference image is missing essential target content.
• ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoning
  13 Mar 2025 1 repository listed
  To this end, we propose ImageScope, a training-free, three-stage framework that leverages collective reasoning to unify LGIR tasks.
• MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval
  19 Dec 2024 1 repository listed
  Despite the rapidly growing demand for multimodal retrieval, progress in this field remains severely constrained by a lack of training data.
• Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval
  15 Dec 2024 1 repository listed
  Existing training-free zero-shot CIR (ZS-CIR) methods often employ a two-stage process: they first generate a caption for the reference image and then use Large Language Models for reasoning to obtain a target…
• Composed Image Retrieval for Training-Free Domain Conversion
  4 Dec 2024 1 repository listed
  This work addresses composed image retrieval in the context of domain conversion, where the content of a query image is retrieved in the domain specified by the query text.
• Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity
  7 Sep 2024 1 repository listed Syntology ran 2 of 2 samples · 0 unverified
  Our approach is simple, easy to implement, and its effectiveness is validated through experiments on the FashionIQ and CIRR datasets.
• An Efficient Post-hoc Framework for Reducing Task Discrepancy of Text Encoders for Composed Image Retrieval
  13 Jun 2024 1 repository listed
  However, we highlight an inherent limitation in these projection-based CIR: a task discrepancy of text encoders between the original pre-training task of the encoders (text ↔ image) and the target CIR task (image + text…
• Composed Image Retrieval for Remote Sensing
  24 May 2024 1 repository listed
  Various attributes can be modified by the textual part, such as shape, color, or context.
• Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives
  17 Apr 2024 1 repository listed Syntology ran 3 of 4 samples · 1 unverified
  In addition, our method also performs well in zero-shot composed image retrieval, providing a new CIR solution for the low-resources scenario.
• MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions
  28 Mar 2024 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  MagicLens is built on a key novel insight: image pairs that naturally occur on the same web pages contain a wide range of implicit relations (e.
• Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval
  24 Mar 2024 1 repository listed Syntology ran 10 of 17 samples · 7 unverified
  The pseudo-word tokens generated in this stream are explicitly aligned with fine-grained semantics in the text embedding space.
• Language-only Efficient Training of Zero-shot Composed Image Retrieval
  4 Dec 2023 1 repository listed Syntology ran 3 of 8 samples · 5 unverified · 8 pointer-only (licence)
  Our LinCIR (Language-only training for CIR) can be trained only with text datasets by a novel self-supervision named self-masking projection (SMP).
• Pretrain like Your Inference: Masked Tuning Improves Zero-Shot Composed Image Retrieval
  13 Nov 2023 1 repository listed Syntology ran 3 of 4 samples · 1 unverified · 4 pointer-only (licence)
  Then, we propose a simple but novel pre-trained masked tuning method, which uses the text and the masked image to learn the modifications of the original image.
• Vision-by-Language for Training-Free Compositional Image Retrieval
  13 Oct 2023 1 repository listed Syntology ran 4 of 8 samples · 4 unverified
  Finally, we show that CIReVL makes CIR human-understandable by composing image and text in a modular fashion in the language domain, thereby making it intervenable, allowing to post-hoc re-align failure cases.
• Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval
  28 Sep 2023 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  Different from Composed Image Retrieval task that requires expensive labels for training task-specific models, Zero-Shot Composed Image Retrieval (ZS-CIR) involves diverse tasks with a broad range of visual content…
• CoVR-2: Automatic Data Construction for Composed Video Retrieval
  28 Aug 2023 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  Composed Image Retrieval (CoIR) has recently gained popularity as a task that considers both text and image queries together, to search for relevant images in a database.
• Zero-shot Composed Text-Image Retrieval
  12 Jun 2023 1 repository listed
  In this paper, we consider the problem of composed image retrieval (CIR), it aims to train a model that can fuse multi-modal information, e.
• CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion
  21 Mar 2023 1 repository listed Syntology ran 3 of 6 samples · 3 unverified
  This paper proposes a novel diffusion-based model, CompoDiff, for solving zero-shot Composed Image Retrieval (ZS-CIR) with latent diffusion.
• Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval
  6 Feb 2023 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  Existing methods rely on supervised learning of CIR models using labeled triplets consisting of the query image, text specification, and the target image.

Syntology lines on 13 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.