Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Quantized Vision-Language Models for Damage Assessment: A Comparative Study of LLaVA-1.5-7B Quantization Levels

Takato Yasuno

Abstract

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: Q4_K_M, Q5_K_M, and Q8\_0 across 254 rebar exposure images. We introduce a 5-point quality evaluation framework assessing damage type recognition, severity classification. Our results demonstrate that Q5_K_M achieves the optimal balance: quality score 3.18$\pm$1.35/5.0, inference time 5.67s/image, and 0.56 quality/sec efficiency -- 8.5% higher quality than Q4_K_M with only 4.5% speed reduction, while matching Q8_0's quality with 25% faster inference. Statistical analysis reveals Q5_K_M exhibits the weakest text-quality correlation (-0.148), indicating consistent performance regardless of description length.

Quantized Vision-Language Models for Damage Assessment: A Comparative Study of LLaVA-1.5-7B Quantization Levels

Abstract

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: Q4_K_M, Q5_K_M, and Q8\_0 across 254 rebar exposure images. We introduce a 5-point quality evaluation framework assessing damage type recognition, severity classification. Our results demonstrate that Q5_K_M achieves the optimal balance: quality score 3.181.35/5.0, inference time 5.67s/image, and 0.56 quality/sec efficiency -- 8.5% higher quality than Q4_K_M with only 4.5% speed reduction, while matching Q8_0's quality with 25% faster inference. Statistical analysis reveals Q5_K_M exhibits the weakest text-quality correlation (-0.148), indicating consistent performance regardless of description length.

Paper Structure

This paper contains 39 sections, 16 equations, 4 figures, 8 tables.

Table of Contents

  1. Introduction
  2. Background and Motivation
  3. Problem Statement and Research Questions
  4. Contributions
  5. Paper Organization
  6. Related Work
  7. Vision-Language Models
  8. Model Quantization for Large Models
  9. Automated Infrastructure Damage Assessment
  10. Methodology
  11. System Architecture
  12. Mathematical Formulation
  13. Vision Analysis with Quantized LLaVA
  14. Quality Evaluation Framework
  15. Statistical Analysis
  16. ...and 24 more sections

Figures (4)

  • Figure 1: End-to-end pipeline architecture. This study focuses on Stage 2 (Vision Analysis) quantization comparison, while other stages remain constant.
  • Figure 2: Comprehensive performance comparison across quantization levels (N=254). Top-left: Average inference time with error bars. Top-right: Model size vs total processing time. Bottom-left: Quality score distributions with baseline reference. Bottom-right: Summary metrics table.
  • Figure 3: Statistical analysis of quantization comparison (N=254). Top row: Quality score, text length, and inference time distributions (violin plots). Middle row: Box plots and scatter plots showing relationships. Bottom: Detailed metrics summary table.
  • Figure 4: Preprocessed input images (N=12) after NLM denoising, resizing to 640×480, and CLAHE enhancement. Parentheses indicate damage level and damage type recognized by the model.