# VQA4CIR: Boosting Composed Image Retrieval with Visual Question Answering

arXiv: https://arxiv.org/abs/2312.12273 · HTML: https://mlsanity.com/paper/2312.12273/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 55 references that are in the map.
- First posted on arXiv 19 Dec 2023.

## Builds on (most cited first, 30 of 40)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (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)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [VideoChat: Chat-Centric Video Understanding](https://mlsanity.com/paper/2305.06355/) (2023)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model](https://mlsanity.com/paper/2304.15010/) (2023)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [A Corpus for Reasoning About Natural Language Grounded in Photographs](https://mlsanity.com/paper/1811.00491/) (2018)
- [ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning](https://mlsanity.com/paper/2309.16650/) (2023)
- [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)
- [AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models](https://mlsanity.com/paper/2308.15366/) (2023)
- [Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection](https://mlsanity.com/paper/2207.03482/) (2022)
- [LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning](https://mlsanity.com/paper/2308.03303/) (2023)
- [CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion](https://mlsanity.com/paper/2303.11916/) (2023)
- [VPGTrans: Transfer Visual Prompt Generator across LLMs](https://mlsanity.com/paper/2305.01278/) (2023)
- [Sentence-level Prompts Benefit Composed Image Retrieval](https://mlsanity.com/paper/2310.05473/) (2023)
- [Compositional Learning of Image-Text Query for Image Retrieval](https://mlsanity.com/paper/2006.11149/) (2020)

## Built on by (most cited first, 11 of 11)

- [Document Haystacks: Vision-Language Reasoning Over Piles of 1000+ Documents](https://mlsanity.com/paper/2411.16740/) (2024)
- [OmniCount: Multi-label Object Counting with Semantic-Geometric Priors](https://mlsanity.com/paper/2403.05435/) (2024)
- [MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks](https://mlsanity.com/paper/2506.07016/) (2025)
- [AURA: A Fine-Grained Benchmark and Decomposed Metric for Audio-Visual Reasoning](https://mlsanity.com/paper/2508.07470/) (2025)
- [DetailFusion: A Dual-branch Framework with Detail Enhancement for Composed Image Retrieval](https://mlsanity.com/paper/2505.17796/) (2025)
- [VisRet: Visualization Improves Knowledge-Intensive Text-to-Image Retrieval](https://mlsanity.com/paper/2505.20291/) (2025)
- [Composed Multi-modal Retrieval: A Survey of Approaches and Applications](https://mlsanity.com/paper/2503.01334/) (2025)
- [Instruction-Aligned Visual Attention for Mitigating Hallucinations in Large Vision-Language Models](https://mlsanity.com/paper/2503.18556/) (2025)
- [DAFM: Dynamic Adaptive Fusion for Multi-Model Collaboration in Composed Image Retrieval](https://mlsanity.com/paper/2511.05020/) (2025)
- [Fusionista2.0: Efficiency Retrieval System for Large-Scale Datasets](https://mlsanity.com/paper/2511.12255/) (2025)
- [FIRE-CIR: Fine-grained Reasoning for Composed Fashion Image Retrieval](https://mlsanity.com/paper/2604.09114/) (2026)

## Abstract (arXiv)

Albeit progress has been made in Composed Image Retrieval (CIR), we empirically find that a certain percentage of failure retrieval results are not consistent with their relative captions. To address this issue, this work provides a Visual Question Answering (VQA) perspective to boost the performance of CIR. The resulting VQA4CIR is a post-processing approach and can be directly plugged into existing CIR methods. Given the top-C retrieved images by a CIR method, VQA4CIR aims to decrease the adverse effect of the failure retrieval results being inconsistent with the relative caption. To find the retrieved images inconsistent with the relative caption, we resort to the "QA generation to VQA" self-verification pipeline. For QA generation, we suggest fine-tuning LLM (e.g., LLaMA) to generate several pairs of questions and answers from each relative caption. We then fine-tune LVLM (e.g., LLaVA) to obtain the VQA model. By feeding the retrieved image and question to the VQA model, one can find the images inconsistent with relative caption when the answer by VQA is inconsistent with the answer in the QA pair. Consequently, the CIR performance can be boosted by modifying the ranks of inconsistently retrieved images. Experimental results show that our proposed method outperforms state-of-the-art CIR methods on the CIRR and Fashion-IQ datasets.