# Unleashing the Capabilities of Large Vision-Language Models for Intelligent Perception of Roadside Infrastructure

arXiv: https://arxiv.org/abs/2601.10551 · HTML: https://mlsanity.com/paper/2601.10551/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Driving VLMs and open-vocabulary detection, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 21 of its 38 references that are in the map.
- First posted on arXiv 15 Jan 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Driving VLMs and open-vocabulary detection](https://mlsanity.com/mllm/driving-vlms-and-open-vocabulary-detection/)

## Builds on (most cited first, 21 of 21)

- [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)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [YOLO-World: Real-Time Open-Vocabulary Object Detection](https://mlsanity.com/paper/2401.17270/) (2024)
- [A Survey on Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2402.00253/) (2024)
- [An Introduction to Vision-Language Modeling](https://mlsanity.com/paper/2405.17247/) (2024)
- [Visual In-Context Learning for Large Vision-Language Models](https://mlsanity.com/paper/2402.11574/) (2024)
- [On the Road with GPT-4V(ision): Early Explorations of Visual-Language Model on Autonomous Driving](https://mlsanity.com/paper/2311.05332/) (2023)
- [Deep Learning for Large-Scale Traffic-Sign Detection and Recognition](https://mlsanity.com/paper/1904.00649/) (2019)
- [OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion](https://mlsanity.com/paper/2407.07844/) (2024)
- [Computer Vision for Road Imaging and Pothole Detection: A State-of-the-Art Review of Systems and Algorithms](https://mlsanity.com/paper/2204.13590/) (2022)
- [Infrastructure-Based Object Detection and Tracking for Cooperative Driving Automation: A Survey](https://mlsanity.com/paper/2201.11871/) (2022)

## Built on by (most cited first, 1 of 1)

- [WHU-Infra3D: A Full-stack Multi-modal Dataset and Benchmark for 3D Roadside Infrastructure Inventory](https://mlsanity.com/paper/2606.09882/) (2026)

## Abstract (arXiv)

Automated perception of urban roadside infrastructure is crucial for smart city management, yet general-purpose models often struggle to capture the necessary fine-grained attributes and domain rules. While Large Vision Language Models (VLMs) excel at open-world recognition, they often struggle to accurately interpret complex facility states in compliance with engineering standards, leading to unreliable performance in real-world applications. To address this, we propose a domain-adapted framework that transforms VLMs into specialized agents for intelligent infrastructure analysis. Our approach integrates a data-efficient fine-tuning strategy with a knowledge-grounded reasoning mechanism. Specifically, we leverage open-vocabulary fine-tuning on Grounding DINO to robustly localize diverse assets with minimal supervision, followed by LoRA-based adaptation on Qwen-VL for deep semantic attribute reasoning. To mitigate hallucinations and enforce professional compliance, we introduce a dual-modality Retrieval-Augmented Generation (RAG) module that dynamically retrieves authoritative industry standards and visual exemplars during inference. Evaluated on a comprehensive new dataset of urban roadside scenes, our framework achieves a detection performance of 58.9 mAP and an attribute recognition accuracy of 95.5%, demonstrating a robust solution for intelligent infrastructure monitoring.