# Vision-Language In-Context Learning Driven Few-Shot Visual Inspection Model

arXiv: https://arxiv.org/abs/2502.09057 · HTML: https://mlsanity.com/paper/2502.09057/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 13 Feb 2025.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization](https://mlsanity.com/paper/2011.08785/) (2020)
- [A Survey of Deep Active Learning](https://mlsanity.com/paper/2009.00236/) (2020)
- [Otter: A Multi-Modal Model with In-Context Instruction Tuning](https://mlsanity.com/paper/2305.03726/) (2023)
- [SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation](https://mlsanity.com/paper/2207.14315/) (2022)
- [LoRA Learns Less and Forgets Less](https://mlsanity.com/paper/2405.09673/) (2024)
- [WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation](https://mlsanity.com/paper/2303.14814/) (2023)
- [An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA](https://mlsanity.com/paper/2109.05014/) (2021)
- [MIMIC-IT: Multi-Modal In-Context Instruction Tuning](https://mlsanity.com/paper/2306.05425/) (2023)
- [Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentation](https://mlsanity.com/paper/2006.16067/) (2020)
- [ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts](https://mlsanity.com/paper/2312.00784/) (2023)
- [Metrics for Multi-Class Classification: an Overview](https://mlsanity.com/paper/2008.05756/) (2020)
- [Is Cosine-Similarity of Embeddings Really About Similarity?](https://mlsanity.com/paper/2403.05440/) (2024)
- [What Makes Multimodal In-Context Learning Work?](https://mlsanity.com/paper/2404.15736/) (2024)
- [Link-Context Learning for Multimodal LLMs](https://mlsanity.com/paper/2308.07891/) (2023)
- [Good Classification Measures and How to Find Them](https://mlsanity.com/paper/2201.09044/) (2022)
- [Benchmarking of Query Strategies: Towards Future Deep Active Learning](https://mlsanity.com/paper/2312.05751/) (2023)

## Abstract (arXiv)

We propose general visual inspection model using Vision-Language Model~(VLM) with few-shot images of non-defective or defective products, along with explanatory texts that serve as inspection criteria. Although existing VLM exhibit high performance across various tasks, they are not trained on specific tasks such as visual inspection. Thus, we construct a dataset consisting of diverse images of non-defective and defective products collected from the web, along with unified formatted output text, and fine-tune VLM. For new products, our method employs In-Context Learning, which allows the model to perform inspections with an example of non-defective or defective image and the corresponding explanatory texts with visual prompts. This approach eliminates the need to collect a large number of training samples and re-train the model for each product. The experimental results show that our method achieves high performance, with MCC of 0.804 and F1-score of 0.950 on MVTec AD in a one-shot manner. Our code is available at~https://github.com/ia-gu/Vision-Language-In-Context-Learning-Driven-Few-Shot-Visual-Inspection-Model.