Sentence-level Prompts Benefit Composed Image Retrieval
2023 · Yang Bai, Xinxing Xu, Yong Liu, et al.
Abstract
Composed image retrieval (CIR) is the task of retrieving specific images by using a query that involves both a reference image and a relative caption. Most existing CIR models adopt the late-fusion strategy to combine visual and language features. Besides, several approaches have also been suggested to generate a pseudo-word token from the reference image, which is further integrated into the relative caption for CIR. However, these pseudo-word-based prompting methods have limitations when target image encompasses complex changes on reference image, e.g., object removal and attribute modification. In this work, we demonstrate that learning an appropriate sentence-level prompt for the relative caption (SPRC) is sufficient for achieving effective composed image retrieval. Instead of relying on pseudo-word-based prompts, we propose to leverage pretrained V-L models, e.g., BLIP-2, to generate sentence-level prompts. By concatenating the learned sentence-level prompt with the relative capti
Authors
(none)
Tags
Stats
Related papers
- Scaling Prompt Instructed Zero Shot Composed Image Retrieval With Image-only Data (2025)0.00
- Instance-level Composed Image Retrieval (2025)0.00
- Compositional Image Retrieval Via Instruction-aware Contrastive Learning (2024)0.00
- A Sanity Check On Composed Image Retrieval (2026)0.00
- Leveraging Large Vision-language Model As User Intent-aware Encoder For Composed Image Retrieval (2024)3.58
- HINT: Composed Image Retrieval With Dual-path Compositional Contextualized Network (2026)0.78
- Infocir: Multimedia Analysis For Composed Image Retrieval (2026)1.24
- Good4cir: Generating Detailed Synthetic Captions For Composed Image Retrieval (2025)0.00