Zero-Shot Vehicle Model Recognition via Text-Based Retrieval-Augmented Generation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chang, Wei-Chia, Chen, Yan-Ann
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917029526634496
author Chang, Wei-Chia
Chen, Yan-Ann
author_facet Chang, Wei-Chia
Chen, Yan-Ann
contents Vehicle make and model recognition (VMMR) is an important task in intelligent transportation systems, but existing approaches struggle to adapt to newly released models. Contrastive Language-Image Pretraining (CLIP) provides strong visual-text alignment, yet its fixed pretrained weights limit performance without costly image-specific finetuning. We propose a pipeline that integrates vision language models (VLMs) with Retrieval-Augmented Generation (RAG) to support zero-shot recognition through text-based reasoning. A VLM converts vehicle images into descriptive attributes, which are compared against a database of textual features. Relevant entries are retrieved and combined with the description to form a prompt, and a language model (LM) infers the make and model. This design avoids large-scale retraining and enables rapid updates by adding textual descriptions of new vehicles. Experiments show that the proposed method improves recognition by nearly 20% over the CLIP baseline, demonstrating the potential of RAG-enhanced LM reasoning for scalable VMMR in smart-city applications.
format Preprint
id arxiv_https___arxiv_org_abs_2510_18502
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Zero-Shot Vehicle Model Recognition via Text-Based Retrieval-Augmented Generation
Chang, Wei-Chia
Chen, Yan-Ann
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
Vehicle make and model recognition (VMMR) is an important task in intelligent transportation systems, but existing approaches struggle to adapt to newly released models. Contrastive Language-Image Pretraining (CLIP) provides strong visual-text alignment, yet its fixed pretrained weights limit performance without costly image-specific finetuning. We propose a pipeline that integrates vision language models (VLMs) with Retrieval-Augmented Generation (RAG) to support zero-shot recognition through text-based reasoning. A VLM converts vehicle images into descriptive attributes, which are compared against a database of textual features. Relevant entries are retrieved and combined with the description to form a prompt, and a language model (LM) infers the make and model. This design avoids large-scale retraining and enables rapid updates by adding textual descriptions of new vehicles. Experiments show that the proposed method improves recognition by nearly 20% over the CLIP baseline, demonstrating the potential of RAG-enhanced LM reasoning for scalable VMMR in smart-city applications.
title Zero-Shot Vehicle Model Recognition via Text-Based Retrieval-Augmented Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2510.18502