Datasets › CIRR

CIRR (Compose Image Retrieval on Real-life images)

Introduced by Zheyuan Liu et al. in Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models9 Aug 2021 archive 2025-07-28

Composed Image Retrieval (or, Image Retreival conditioned on Language Feedback) is a relatively new retrieval task, where an input query consists of an image and short textual description of how to modify the image.

For humans, the advantage of a bi-modal query is clear: some concepts and attributes are more succinctly described visually, others through language. By cross-referencing the two modalities, a reference image can capture the general gist of a scene, while the text can specify finer details.

We identify a major challenge of this task as the inherent ambiguity in knowing what information is important (typically one object of interest in the scene) and what can be ignored (e.g., the background and other irrelevant objects).

We release the first dataset of open-domain, real-life images with human-generated modification sentences, which support research on one-shot composed image retrieval, dialogue systems, fine-grained visiolinguistic reasoning, and more.

Benchmarks archive 2025-07-28

All 3 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

Syntology 5 newer papers were judged to report on this dataset's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): Zero-Shot Composed Image Retrieval (ZS-CIR) · CIRR (3 judged, 0 placed), Composed Image Retrieval (CoIR) · CIRR (3 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

Papers archive 2025-07-28

papers with a benchmark row: 35 · with a code link: 32 · where Syntology ran a sample: 16 (12 with a run with no instrument failure, 4 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (16 of 35 with a benchmark row: 12 with a run with no instrument failure, 4 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 35 of 35 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 61. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
TMCIR: Token Merge Benefits Composed Image Retrieval 0 1 15 Apr 2025 not harvested
CoLLM: A Large Language Model for Composed Image Retrieval 1 3 25 Mar 2025 not harvested
ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoning 1 1 13 Mar 2025 not harvested
SCOT: Self-Supervised Contrastive Pretraining For Zero-Shot Compositional Retrieval 0 1 12 Jan 2025 not harvested
MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval 1 1 19 Dec 2024 not harvested
Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval 1 3 15 Dec 2024 not harvested
Imagine and Seek: Improving Composed Image Retrieval with an Imagined Proxy 0 2 24 Nov 2024 not harvested
Semantic Editing Increment Benefits Zero-Shot Composed Image Retrieval 2 3 28 Oct 2024 not harvested
Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity 1 4 7 Sep 2024 official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified
LDRE: LLM-based Divergent Reasoning and Ensemble for Zero-Shot Composed Image Retrieval 2 3 11 Jul 2024 not harvested
An Efficient Post-hoc Framework for Reducing Task Discrepancy of Text Encoders for Composed Image Retrieval 1 2 13 Jun 2024 not harvested
VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval 1 1 6 Jun 2024 official: harvested, nothing ran · 0 ran · 2 unverified
CaLa: Complementary Association Learning for Augmenting Composed Image Retrieval 1 1 29 May 2024 not harvested
iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval 2 4 5 May 2024 official: no sample here; runs from other or unrecorded repositories · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (4 pointer-only for licence)
Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives 1 2 17 Apr 2024 official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified
MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions 1 4 28 Mar 2024 official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified
Language-only Efficient Training of Zero-shot Composed Image Retrieval 1 2 4 Dec 2023 official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified (8 pointer-only for licence)
Pretrain like Your Inference: Masked Tuning Improves Zero-Shot Composed Image Retrieval 1 2 13 Nov 2023 official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (4 pointer-only for licence)
Vision-by-Language for Training-Free Compositional Image Retrieval 1 3 13 Oct 2023 official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified (2 pointer-only for licence)
Sentence-level Prompts Benefit Composed Image Retrieval 1 2 9 Oct 2023 official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified (8 pointer-only for licence)
Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval 1 1 28 Sep 2023 official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified
CoVR-2: Automatic Data Construction for Composed Video Retrieval 1 2 28 Aug 2023 official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified
Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features 2 1 22 Aug 2023 official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified
Zero-shot Composed Text-Image Retrieval 1 1 12 Jun 2023 not harvested
Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder 2 1 25 May 2023 official (archive's flag): 4 ran · 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 (1 pointer-only for licence)
Bi-directional Training for Composed Image Retrieval via Text Prompt Learning 1 1 29 Mar 2023 not harvested
Zero-Shot Composed Image Retrieval with Textual Inversion 2 2 27 Mar 2023 not harvested
CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion 1 2 21 Mar 2023 official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (1 pointer-only for licence)
Data Roaming and Quality Assessment for Composed Image Retrieval 1 2 16 Mar 2023 not harvested
Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval 1 1 6 Feb 2023 official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified
Conditioned and Composed Image Retrieval Combining and Partially Fine-Tuning CLIP-Based Features 2 1 19 Jun 2022 not harvested
"This is my unicorn, Fluffy": Personalizing frozen vision-language representations 2 1 4 Apr 2022 official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (1 pointer-only for licence)
ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity 1 1 15 Mar 2022 not harvested
Effective Conditioned and Composed Image Retrieval Combining CLIP-Based Features 2 1 1 Jan 2022 not harvested
Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models 3 1 9 Aug 2021 official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified

Dataset loaders archive 2025-07-28

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

MIT License

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • CIRR

1 variant name, as the archive lists them.

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