# GPT-4V-AD: Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly Detection

arXiv: https://arxiv.org/abs/2311.02612 · HTML: https://mlsanity.com/paper/2311.02612/

## Key facts

- Cited by 23 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 31 of its 42 references that are in the map.
- First posted on arXiv 5 Nov 2023.

## Placed in

- Multimodal LLMs / vision-language models / [Chart understanding and anomaly detection](https://mlsanity.com/mllm/chart-understanding-and-anomaly-detection/)

## Builds on (most cited first, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)](https://mlsanity.com/paper/2309.17421/) (2023)
- [PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization](https://mlsanity.com/paper/2011.08785/) (2020)
- [CutPaste: Self-Supervised Learning for Anomaly Detection and Localization](https://mlsanity.com/paper/2104.04015/) (2021)
- [DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection](https://mlsanity.com/paper/2108.07610/) (2021)
- [Anomaly Detection via Reverse Distillation from One-Class Embedding](https://mlsanity.com/paper/2201.10703/) (2022)
- [SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation](https://mlsanity.com/paper/2207.14315/) (2022)
- [Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings](https://mlsanity.com/paper/1911.02357/) (2019)
- [WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation](https://mlsanity.com/paper/2303.14814/) (2023)
- [Sub-Image Anomaly Detection with Deep Pyramid Correspondences](https://mlsanity.com/paper/2005.02357/) (2020)
- [Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V](https://mlsanity.com/paper/2310.11441/) (2023)
- [AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection](https://mlsanity.com/paper/2310.18961/) (2023)
- [A Unified Model for Multi-class Anomaly Detection](https://mlsanity.com/paper/2206.03687/) (2022)
- [SimpleNet: A Simple Network for Image Anomaly Detection and Localization](https://mlsanity.com/paper/2303.15140/) (2023)
- [Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows](https://mlsanity.com/paper/2008.12577/) (2020)
- [AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models](https://mlsanity.com/paper/2308.15366/) (2023)
- [APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD](https://mlsanity.com/paper/2305.17382/) (2023)
- [Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localization](https://mlsanity.com/paper/2109.15222/) (2021)
- [Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2203.00259/) (2022)
- [Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcore](https://mlsanity.com/paper/2301.12082/) (2023)
- [Segment Any Anomaly without Training via Hybrid Prompt Regularization](https://mlsanity.com/paper/2305.10724/) (2023)
- [CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection](https://mlsanity.com/paper/2311.00453/) (2023)
- [Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth Evaluation](https://mlsanity.com/paper/2310.16809/) (2023)

## Built on by (most cited first, 23 of 23)

- [AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model](https://mlsanity.com/paper/2312.05767/) (2023)
- [A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospect](https://mlsanity.com/paper/2401.16402/) (2024)
- [Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detection](https://mlsanity.com/paper/2312.07495/) (2023)
- [MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection](https://mlsanity.com/paper/2410.09453/) (2024)
- [DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection](https://mlsanity.com/paper/2312.06607/) (2023)
- [List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs](https://mlsanity.com/paper/2404.16375/) (2024)
- [Effectiveness Assessment of Recent Large Vision-Language Models](https://mlsanity.com/paper/2403.04306/) (2024)
- [Large Language Models for Anomaly and Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2409.01980/) (2024)
- [M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoising](https://mlsanity.com/paper/2406.02263/) (2024)
- [LogiCode: an LLM-Driven Framework for Logical Anomaly Detection](https://mlsanity.com/paper/2406.04687/) (2024)
- [Long-Tailed Anomaly Detection with Learnable Class Names](https://mlsanity.com/paper/2403.20236/) (2024)
- [UrbanSAM: Learning Invariance-Inspired Adapters for Segment Anything Models in Urban Construction](https://mlsanity.com/paper/2502.15199/) (2025)
- [Foundation Models and Transformers for Anomaly Detection: A Survey](https://mlsanity.com/paper/2507.15905/) (2025)
- [CMOOD: Concept-based Multi-label OOD Detection](https://mlsanity.com/paper/2411.13578/) (2024)
- [CableInspect-AD: An Expert-Annotated Anomaly Detection Dataset](https://mlsanity.com/paper/2409.20353/) (2024)
- [A Survey on Foundation-Model-Based Industrial Defect Detection](https://mlsanity.com/paper/2502.19106/) (2025)
- [AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparison](https://mlsanity.com/paper/2603.13779/) (2026)
- [InsightX Agent: An LMM-based Agentic Framework with Integrated Tools for Reliable X-ray NDT Analysis](https://mlsanity.com/paper/2507.14899/) (2025)
- [IADGPT: Unified LVLM for Few-Shot Industrial Anomaly Detection, Localization, and Reasoning via In-Context Learning](https://mlsanity.com/paper/2508.10681/) (2025)
- [Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts](https://mlsanity.com/paper/2507.16946/) (2025)
- [MMR-AD: A Large-Scale Multimodal Dataset for Benchmarking General Anomaly Detection with Multimodal Large Language Models](https://mlsanity.com/paper/2604.10971/) (2026)
- [Patch is Enough: Naturalistic Adversarial Patch against Vision-Language Pre-training Models](https://mlsanity.com/paper/2410.04884/) (2024)
- [Zero-Shot Anomaly Detection in Battery Thermal Images Using Visual Question Answering with Prior Knowledge](https://mlsanity.com/paper/2505.16674/) (2025)

## Abstract (arXiv)

Large Multimodal Model (LMM) GPT-4V(ision) endows GPT-4 with visual grounding capabilities, making it possible to handle certain tasks through the Visual Question Answering (VQA) paradigm. This paper explores the potential of VQA-oriented GPT-4V in the recently popular visual Anomaly Detection (AD) and is the first to conduct qualitative and quantitative evaluations on the popular MVTec AD and VisA datasets. Considering that this task requires both image-/pixel-level evaluations, the proposed GPT-4V-AD framework contains three components: textbftextit1) Granular Region Division, textbftextit2) Prompt Designing, textbftextit3) Text2Segmentation for easy quantitative evaluation, and have made some different attempts for comparative analysis. The results show that GPT-4V can achieve certain results in the zero-shot AD task through a VQA paradigm, such as achieving image-level 77.1/88.0 and pixel-level 68.0/76.6 AU-ROCs on MVTec AD and VisA datasets, respectively. However, its performance still has a certain gap compared to the state-of-the-art zero-shot method, eg, WinCLIP and CLIP-AD, and further researches are needed. This study provides a baseline reference for the research of VQA-oriented LMM in the zero-shot AD task, and we also post several possible future works. Code is available at urlhttps://github.com/zhangzjn/GPT-4V-AD.