mlsanityData to 14 Oct 2026

CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion

arXiv 2303.11916 ↗First posted 21 Mar 2023cs.CV cs.IRcited by 85

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

This paper proposes a novel diffusion-based model, CompoDiff, for solving zero-shot Composed Image Retrieval (ZS-CIR) with latent diffusion. This paper also introduces a new synthetic dataset, named SynthTriplets18M, with 18.8 million reference images, conditions, and corresponding target image triplets to train CIR models. CompoDiff and SynthTriplets18M tackle the shortages of the previous CIR approaches, such as poor generalizability due to the small dataset scale and the limited types of conditions. CompoDiff not only achieves a new state-of-the-art on four ZS-CIR benchmarks, including FashionIQ, CIRR, CIRCO, and GeneCIS, but also enables a more versatile and controllable CIR by accepting various conditions, such as negative text, and image mask conditions. CompoDiff also shows the controllability of the condition strength between text and image queries and the trade-off between inference speed and performance, which are unavailable with existing CIR methods. The code and dataset are available at https://github.com/navervision/CompoDiff

Key facts. Cited by 85 papers in the map (data through 14 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 53 of its 87 references that are in the map. First posted on arXiv 21 Mar 2023.

Builds on

53 of 87 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023Adding Conditional Control to Text-to-Image Diffusion Models10 Feb
  2. 2022Unite and Conquer: Plug & Play Multi-Modal Synthesis using Diffusion Models1 Dec
  3. 2022InstructPix2Pix: Learning to Follow Image Editing Instructions17 Nov
  4. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers2 Nov
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latents13 Apr

Other references · 48

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  6. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  7. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  8. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  9. 2020Denoising Diffusion Implicit Modelscited by 9,781
  10. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  11. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  12. 2022Scalable Diffusion Models with Transformerscited by 6,054
36 more
  1. 2022Classifier-Free Diffusion Guidancecited by 5,847
  2. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  3. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  4. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  5. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  6. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  7. 2017Billion-scale similarity search with GPUscited by 2,497
  8. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,431
  9. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,850
  10. 2023Consistency Modelscited by 1,822
  11. 2015Microsoft COCO Captions: Data Collection and Evaluation Servercited by 1,462
  12. 2022On Distillation of Guided Diffusion Modelscited by 725
  13. 2021Image Segmentation Using Text and Image Promptscited by 512
  14. 2018A Corpus for Reasoning About Natural Language Grounded in Photographscited by 459
  15. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  16. 2020A Metric Learning Reality Checkcited by 321
  17. 2021Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Modelscited by 251
  18. 2018Composing Text and Image for Image Retrieval - An Empirical Odysseycited by 236
  19. 2023Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrievalcited by 156
  20. 2021Probabilistic Embeddings for Cross-Modal Retrievalcited by 151
  21. 2020Learning the Best Pooling Strategy for Visual Semantic Embeddingcited by 137
  22. 2017Automatic Spatially-aware Fashion Concept Discoverycited by 134
  23. 2021Learning to Predict Visual Attributes in the Wildcited by 96
  24. 2018Dialog-based Interactive Image Retrievalcited by 84
  25. 2019Polysemous Visual-Semantic Embedding for Cross-Modal Retrievalcited by 83
  26. 2022ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similaritycited by 83
  27. 2020Compositional Learning of Image-Text Query for Image Retrievalcited by 57
  28. 2020Modality-Agnostic Attention Fusion for visual search with text feedbackcited by 51
  29. 2020Crisscrossed Captions: Extended Intramodal and Intermodal Semantic Similarity Judgments for MS-COCOcited by 46
  30. 2021ViDT: An Efficient and Effective Fully Transformer-based Object Detectorcited by 46
  31. 2022Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularizationcited by 45
  32. 2022ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCOcited by 37
  33. 2021RTIC: Residual Learning for Text and Image Composition using Graph Convolutional Networkcited by 27
  34. 2020SAC: Semantic Attention Composition for Text-Conditioned Image Retrievalcited by 23
  35. 2020CurlingNet: Compositional Learning between Images and Text for Fashion IQ Datacited by 21
  36. 2022Image Search with Text Feedback by Additive Attention Compositional Learningcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 8; 2024: 20; 2025: 31; 2026: 26.

85 papers.

Sort:

By area:

  1. 2024MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructionscited by 119
  2. 2023Vision-by-Language for Training-Free Compositional Image Retrievalcited by 103
  3. 2024MegaPairs: Massive Data Synthesis For Universal Multimodal Retrievalcited by 84
  4. 2023Sentence-level Prompts Benefit Composed Image Retrievalcited by 59
  5. 2023CoVR-2: Automatic Data Construction for Composed Video Retrievalcited by 52
  6. 2025FineCIR: Explicit Parsing of Fine-Grained Modification Semantics for Composed Image Retrievalcited by 42
  7. 2024Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrievalcited by 36
  8. 2023Zero-shot Composed Text-Image Retrievalcited by 32
  9. 2024DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factorscited by 32
  10. 2024Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrievalcited by 32
  11. 2023Language-only Efficient Training of Zero-shot Composed Image Retrievalcited by 27
  12. 2024Composed Video Retrieval via Enriched Context and Discriminative Embeddingscited by 26
38 more
  1. 2024EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrievalcited by 21
  2. 2025CoLLM: A Large Language Model for Composed Image Retrievalcited by 21
  3. 2024Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negativescited by 20
  4. 2024Imagine and Seek: Improving Composed Image Retrieval with an Imagined Proxycited by 18
  5. 2025Missing Target-Relevant Information Prediction with World Model for Accurate Zero-Shot Composed Image Retrievalcited by 18
  6. 2025A Comprehensive Survey on Composed Image Retrievalcited by 17
  7. 2024The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspectivecited by 15
  8. 2023Pretrain like Your Inference: Masked Tuning Improves Zero-Shot Composed Image Retrievalcited by 14
  9. 2024Image2Sentence based Asymmetrical Zero-shot Composed Image Retrievalcited by 14
  10. 2024Visual Delta Generator with Large Multi-modal Models for Semi-supervised Composed Image Retrievalcited by 13
  11. 2024Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similaritycited by 12
  12. 2025Instance-Level Composed Image Retrievalcited by 12
  13. 2023VQA4CIR: Boosting Composed Image Retrieval with Visual Question Answeringcited by 11
  14. 2024Leveraging Large Language Models for Multimodal Searchcited by 11
  15. 2025ELIP: Enhanced Visual-Language Foundation Models for Image Retrievalcited by 9
  16. 2026CoVR-R:Reason-Aware Composed Video Retrievalcited by 8
  17. 2025Scale Up Composed Image Retrieval Learning via Modification Text Generationcited by 7
  18. 2025ConText-CIR: Learning from Concepts in Text for Composed Image Retrievalcited by 7
  19. 2024ChatSearch: a Dataset and a Generative Retrieval Model for General Conversational Image Retrievalcited by 6
  20. 2025Beyond Simple Edits: Composed Video Retrieval with Dense Modificationscited by 6
  21. 2024A Survey of Multimodal Composite Editing and Retrievalcited by 5
  22. 2025MOON2.0: Dynamic Modality-balanced Multimodal Representation Learning for E-commerce Product Understandingcited by 5
  23. 2024Pseudo-triplet Guided Few-shot Composed Image Retrievalcited by 4
  24. 2024Composed Image Retrieval for Training-Free Domain Conversioncited by 4
  25. 2025good4cir: Generating Detailed Synthetic Captions for Composed Image Retrievalcited by 4
  26. 2025TMCIR: Token Merge Benefits Composed Image Retrievalcited by 4
  27. 2025DetailFusion: A Dual-branch Framework with Detail Enhancement for Composed Image Retrievalcited by 4
  28. 2025Multiplicity is an Inevitable and Inherent Challenge in Multimodal Learningcited by 4
  29. 2025From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained Videoscited by 4
  30. 2025PDV: Prompt Directional Vectors for Zero-shot Composed Image Retrievalcited by 3
  31. 2025FAR-Net: Multi-Stage Fusion Network with Enhanced Semantic Alignment and Adaptive Reconciliation for Composed Image Retrievalcited by 3
  32. 2026WISER: Wider Search, Deeper Thinking, and Adaptive Fusion for Training-Free Zero-Shot Composed Image Retrievalcited by 3
  33. 2023Benchmarking Robustness of Text-Image Composed Retrievalcited by 2
  34. 2024An Efficient Post-hoc Framework for Reducing Task Discrepancy of Text Encoders for Composed Image Retrievalcited by 2
  35. 2024Modality and Task Adaptation for Enhanced Zero-shot Composed Image Retrievalcited by 2
  36. 2025SCOT: Self-Supervised Contrastive Pretraining For Zero-Shot Compositional Retrievalcited by 2
  37. 2025Composed Multi-modal Retrieval: A Survey of Approaches and Applicationscited by 2
  38. 2025Data-Efficient Generalization for Zero-shot Composed Image Retrievalcited by 2

50 most cited of 85 All 85 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Training-Free Pseudo-Fusion for Composed Image Retrieval with Diffusion Models and Multimodal Large Language Models
  2. 2025Soft Filtering: Guiding Zero-shot Composed Image Retrieval with Prescriptive and Proscriptive Constraints
  3. 2026PinPoint: Evaluation of Composed Image Retrieval with Explicit Negatives, Multi-Image Queries, and Paraphrase Testing
  4. 2025Multimodal Reasoning Agent for Zero-Shot Composed Image Retrieval
  5. 2026Never Seen Before: Benchmarking Genuine Zero-Shot Composed Image Retrieval with Consistent Video-Sourced Datasets
  6. 2026Generating a Paracosm for Training-Free Zero-Shot Composed Image Retrieval
  7. 2025Diffusion Augmented Retrieval: A Training-Free Approach to Interactive Text-to-Image Retrieval
  8. 2024HyCIR: Boosting Zero-Shot Composed Image Retrieval with Synthetic Labels