# A Sanity Check on Composed Image Retrieval

arXiv: https://arxiv.org/abs/2604.12904 · HTML: https://mlsanity.com/paper/2604.12904/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 48 of its 56 references that are in the map.
- First posted on arXiv 14 Apr 2026.

## Builds on (most cited first, 30 of 48)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [nocaps: novel object captioning at scale](https://mlsanity.com/paper/1812.08658/) (2018)
- [Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models](https://mlsanity.com/paper/2108.04024/) (2021)
- [Teaching CLIP to Count to Ten](https://mlsanity.com/paper/2302.12066/) (2023)
- [HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing](https://mlsanity.com/paper/2404.09990/) (2024)
- [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)
- [MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions](https://mlsanity.com/paper/2403.19651/) (2024)
- [LamRA: Large Multimodal Model as Your Advanced Retrieval Assistant](https://mlsanity.com/paper/2412.01720/) (2024)
- [Vision-by-Language for Training-Free Compositional Image Retrieval](https://mlsanity.com/paper/2310.09291/) (2023)
- [CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion](https://mlsanity.com/paper/2303.11916/) (2023)
- [Intelligent Grimm -- Open-ended Visual Storytelling via Latent Diffusion Models](https://mlsanity.com/paper/2306.00973/) (2023)
- [Sentence-level Prompts Benefit Composed Image Retrieval](https://mlsanity.com/paper/2310.05473/) (2023)
- [SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass](https://mlsanity.com/paper/2508.15769/) (2025)
- [Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features](https://mlsanity.com/paper/2308.11485/) (2023)
- [Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval](https://mlsanity.com/paper/2309.16137/) (2023)
- [Data Roaming and Quality Assessment for Composed Image Retrieval](https://mlsanity.com/paper/2303.09429/) (2023)
- [Learn "No" to Say "Yes" Better: Improving Vision-Language Models via Negations](https://mlsanity.com/paper/2403.20312/) (2024)

## Abstract (arXiv)

Composed Image Retrieval (CIR) aims to retrieve a target image based on a query composed of a reference image, and a relative caption that specifies the desired modification. Despite the rapid development of CIR models, their performance is not well characterized by existing benchmarks, which inherently contain indeterminate queries degrading the evaluation (i.e., multiple candidate images, rather than solely the target image, meet the query criteria), and have not considered their effectiveness in the context of the multi-round system. Motivated by this, we consider improving the evaluation procedure from two aspects: 1) we introduce FISD, a Fully-Informed Semantically-Diverse benchmark, which employs generative models to precisely control the variables of reference-target image pairs, enabling a more accurate evaluation of CIR methods across six dimensions, without query ambiguity; 2) we propose an automatic multi-round agentic evaluation framework to probe the potential of the existing models in the interactive scenarios. By observing how models adapt and refine their choices over successive rounds of queries, this framework provides a more realistic appraisal of their efficacy in practical applications. Extensive experiments and comparisons prove the value of our novel evaluation on typical CIR methods.