Quantized Vision-Language Models for Damage Assessment: A Comparative Study of LLaVA-1.5-7B Quantization Levels
On the map: Multimodal LLMs / vision-language models → Chart understanding and anomaly detection
Abstract (arXiv)
Bridge infrastructure inspection is a critical but labor-intensive task requiring expert assessment of structural damage such as rebar exposure, cracking, and corrosion. This paper presents a comprehensive study of quantized Vision-Language Models (VLMs) for automated bridge damage assessment, focusing on the trade-offs between description quality, inference speed, and resource requirements. We develop an end-to-end pipeline combining LLaVA-1.5-7B for visual damage analysis, structured JSON extraction, and rule-based priority scoring. To enable deployment on consumer-grade GPUs, we conduct a systematic comparison of three quantization levels: Q4KM, Q5KM, and Q80 across 254 rebar exposure images. We introduce a 5-point quality evaluation framework assessing damage type recognition, severity classification. Our results demonstrate that Q5KM achieves the optimal balance: quality score 3.18±1.35/5.0, inference time 5.67s/image, and 0.56 quality/sec efficiency -- 8.5% higher quality than Q4KM with only 4.5% speed reduction, while matching Q80's quality with 25% faster inference. Statistical analysis reveals Q5KM exhibits the weakest text-quality correlation (-0.148), indicating consistent performance regardless of description length.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Chart understanding and anomaly detection, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 13 of its 38 references that are in the map. First posted on arXiv 24 Mar 2026.
Builds on
13 of 38 references.
References · 13
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2023Visual Instruction Tuningcited by 7,869
- 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
- 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
- 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
- 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
- 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
- 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
- 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
- 2023CogVLM: Visual Expert for Pretrained Language Modelscited by 708
- 2026Multi-stage Bridge Inspection System: Integrating Foundation Models with Location Anonymizationcited by 2
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2025SDIGLM: Leveraging Large Language Models and Multi-Modal Chain of Thought for Structural Damage Identification
- 2026Vision-Language Foundation Models for Comprehensive Automated Pavement Condition Assessment
- 2026Edge-Optimized Vision-Language Models for Underground Infrastructure Assessment
- 2026Grounding Agentic VLMs with Dedicated Segmentation for Fine-Grained Vehicle Damage Assessment
- 2025LVLMs as inspectors: an agentic framework for category-level structural defect annotation
- 2025Survey of Quantization Techniques for On-Device Vision-based Crack Detection
- 2025Effective Damage Data Generation by Fusing Imagery with Human Knowledge Using Vision-Language Models
- 2026From Pixels to Semantics: A Multi-Stage AI Framework for Structural Damage Detection in Satellite Imagery