# Visual Delta Generator with Large Multi-modal Models for Semi-supervised Composed Image Retrieval

arXiv: https://arxiv.org/abs/2404.15516 · HTML: https://mlsanity.com/paper/2404.15516/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 34 of its 52 references that are in the map.
- First posted on arXiv 23 Apr 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Document understanding and multimodal RAG](https://mlsanity.com/mllm/document-understanding-and-multimodal-rag/)

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [EVA: Exploring the Limits of Masked Visual Representation Learning at Scale](https://mlsanity.com/paper/2211.07636/) (2022)
- [A Corpus for Reasoning About Natural Language Grounded in Photographs](https://mlsanity.com/paper/1811.00491/) (2018)
- [Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models](https://mlsanity.com/paper/2108.04024/) (2021)
- [Composing Text and Image for Image Retrieval - An Empirical Odyssey](https://mlsanity.com/paper/1812.07119/) (2018)
- [Zero-Shot Composed Image Retrieval with Textual Inversion](https://mlsanity.com/paper/2303.15247/) (2023)
- [Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval](https://mlsanity.com/paper/2302.03084/) (2023)
- [Grounding Language Models to Images for Multimodal Inputs and Outputs](https://mlsanity.com/paper/2301.13823/) (2023)
- ["This is my unicorn, Fluffy": Personalizing frozen vision-language representations](https://mlsanity.com/paper/2204.01694/) (2022)
- [Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training](https://mlsanity.com/paper/2301.02280/) (2023)
- [CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion](https://mlsanity.com/paper/2303.11916/) (2023)

## Built on by (most cited first, 13 of 13)

- [Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation](https://mlsanity.com/paper/2502.08826/) (2025)
- [CoLLM: A Large Language Model for Composed Image Retrieval](https://mlsanity.com/paper/2503.19910/) (2025)
- [Missing Target-Relevant Information Prediction with World Model for Accurate Zero-Shot Composed Image Retrieval](https://mlsanity.com/paper/2503.17109/) (2025)
- [HyCIR: Boosting Zero-Shot Composed Image Retrieval with Synthetic Labels](https://mlsanity.com/paper/2407.05795/) (2024)
- [Multimodal Reasoning Agent for Zero-Shot Composed Image Retrieval](https://mlsanity.com/paper/2505.19952/) (2025)
- [Mitigating Semantic Collapse in Partially Relevant Video Retrieval](https://mlsanity.com/paper/2510.27432/) (2025)
- [Composed Image Retrieval for Training-Free Domain Conversion](https://mlsanity.com/paper/2412.03297/) (2024)
- [SCOT: Self-Supervised Contrastive Pretraining For Zero-Shot Compositional Retrieval](https://mlsanity.com/paper/2501.08347/) (2025)
- [Composed Multi-modal Retrieval: A Survey of Approaches and Applications](https://mlsanity.com/paper/2503.01334/) (2025)
- [Heterogeneous Uncertainty-Guided Composed Image Retrieval with Fine-Grained Probabilistic Learning](https://mlsanity.com/paper/2601.11393/) (2026)
- [CoVA: Text-Guided Composed Video Retrieval for Audio-Visual Content](https://mlsanity.com/paper/2601.22508/) (2026)
- [AutoComPose: Automatic Generation of Pose Transition Descriptions for Composed Pose Retrieval Using Multimodal LLMs](https://mlsanity.com/paper/2503.22884/) (2025)
- [A Sanity Check on Composed Image Retrieval](https://mlsanity.com/paper/2604.12904/) (2026)

## Abstract (arXiv)

Composed Image Retrieval (CIR) is a task that retrieves images similar to a query, based on a provided textual modification. Current techniques rely on supervised learning for CIR models using labeled triplets of the reference image, text, target image. These specific triplets are not as commonly available as simple image-text pairs, limiting the widespread use of CIR and its scalability. On the other hand, zero-shot CIR can be relatively easily trained with image-caption pairs without considering the image-to-image relation, but this approach tends to yield lower accuracy. We propose a new semi-supervised CIR approach where we search for a reference and its related target images in auxiliary data and learn our large language model-based Visual Delta Generator (VDG) to generate text describing the visual difference (i.e., visual delta) between the two. VDG, equipped with fluent language knowledge and being model agnostic, can generate pseudo triplets to boost the performance of CIR models. Our approach significantly improves the existing supervised learning approaches and achieves state-of-the-art results on the CIR benchmarks.