SQUARE: Semantic Query-Augmented Fusion and Efficient Batch Reranking for Training-free Zero-Shot Composed Image Retrieval
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915525408325632 |
|---|---|
| author | Wu, Ren-Di Lin, Yu-Yen Yang, Huei-Fang |
| author_facet | Wu, Ren-Di Lin, Yu-Yen Yang, Huei-Fang |
| contents | Composed Image Retrieval (CIR) aims to retrieve target images that preserve the visual content of a reference image while incorporating user-specified textual modifications. Training-free zero-shot CIR (ZS-CIR) approaches, which require no task-specific training or labeled data, are highly desirable, yet accurately capturing user intent remains challenging. In this paper, we present SQUARE, a novel two-stage training-free framework that leverages Multimodal Large Language Models (MLLMs) to enhance ZS-CIR. In the Semantic Query-Augmented Fusion (SQAF) stage, we enrich the query embedding derived from a vision-language model (VLM) such as CLIP with MLLM-generated captions of the target image. These captions provide high-level semantic guidance, enabling the query to better capture the user's intent and improve global retrieval quality. In the Efficient Batch Reranking (EBR) stage, top-ranked candidates are presented as an image grid with visual marks to the MLLM, which performs joint visual-semantic reasoning across all candidates. Our reranking strategy operates in a single pass and yields more accurate rankings. Experiments show that SQUARE, with its simplicity and effectiveness, delivers strong performance on four standard CIR benchmarks. Notably, it maintains high performance even with lightweight pre-trained, demonstrating its potential applicability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_26330 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SQUARE: Semantic Query-Augmented Fusion and Efficient Batch Reranking for Training-free Zero-Shot Composed Image Retrieval Wu, Ren-Di Lin, Yu-Yen Yang, Huei-Fang Computer Vision and Pattern Recognition Information Retrieval 68U10, 68P20, 68T10, 68T07, 68T45, 68T50 I.4; H.3; I.5 Composed Image Retrieval (CIR) aims to retrieve target images that preserve the visual content of a reference image while incorporating user-specified textual modifications. Training-free zero-shot CIR (ZS-CIR) approaches, which require no task-specific training or labeled data, are highly desirable, yet accurately capturing user intent remains challenging. In this paper, we present SQUARE, a novel two-stage training-free framework that leverages Multimodal Large Language Models (MLLMs) to enhance ZS-CIR. In the Semantic Query-Augmented Fusion (SQAF) stage, we enrich the query embedding derived from a vision-language model (VLM) such as CLIP with MLLM-generated captions of the target image. These captions provide high-level semantic guidance, enabling the query to better capture the user's intent and improve global retrieval quality. In the Efficient Batch Reranking (EBR) stage, top-ranked candidates are presented as an image grid with visual marks to the MLLM, which performs joint visual-semantic reasoning across all candidates. Our reranking strategy operates in a single pass and yields more accurate rankings. Experiments show that SQUARE, with its simplicity and effectiveness, delivers strong performance on four standard CIR benchmarks. Notably, it maintains high performance even with lightweight pre-trained, demonstrating its potential applicability. |
| title | SQUARE: Semantic Query-Augmented Fusion and Efficient Batch Reranking for Training-free Zero-Shot Composed Image Retrieval |
| topic | Computer Vision and Pattern Recognition Information Retrieval 68U10, 68P20, 68T10, 68T07, 68T45, 68T50 I.4; H.3; I.5 |
| url | https://arxiv.org/abs/2509.26330 |