mlsanityData to 7 Oct 2026

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

arXiv 2502.09057 ↗First posted 13 Feb 2025cs.CVcited by 0

On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning

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.

Key facts. No citing papers in the map yet (data through 7 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.

Builds on

25 of 39 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2016Layer Normalizationcited by 5,579
  5. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  6. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,105
  7. 2023A Survey on Multimodal Large Language Modelscited by 898
  8. 2023Shikra: Unleashing Multimodal LLM's Referential Dialogue Magiccited by 891
  9. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  10. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
  11. 2023Otter: A Multi-Modal Model with In-Context Instruction Tuningcited by 548
  12. 2020A Survey of Deep Active Learningcited by 547
13 more
  1. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
  2. 2024LoRA Learns Less and Forgets Lesscited by 313
  3. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 311
  4. 2021An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQAcited by 298
  5. 2023MIMIC-IT: Multi-Modal In-Context Instruction Tuningcited by 264
  6. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  7. 2023ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Promptscited by 160
  8. 2020Metrics for Multi-Class Classification: an Overviewcited by 140
  9. 2024Is Cosine-Similarity of Embeddings Really About Similarity?cited by 89
  10. 2024What Makes Multimodal In-Context Learning Work?cited by 54
  11. 2023Link-Context Learning for Multimodal LLMscited by 24
  12. 2022Good Classification Measures and How to Find Themcited by 11
  13. 2023Benchmarking of Query Strategies: Towards Future Deep Active Learningcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025InspectVLM: Unified in Theory, Unreliable in Practice
  2. 2026Zero-Shot Learning in Industrial Scenarios: New Large-Scale Benchmark, Challenges and Baseline
  3. 2026Answer-Conditioned Chain-of-Thought Distillation for Few-Shot Industrial Vision with Small VLMs
  4. 2024Can Visual Language Models Replace OCR-Based Visual Question Answering Pipelines in Production? A Case Study in Retail
  5. 2025Trust the Model: Compact VLMs as In-Context Judges for Image-Text Data Quality
  6. 2025Weaving Context Across Images: Improving Vision-Language Models through Focus-Centric Visual Chains
  7. 2023Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification
  8. 2022Vision-Language Pre-training: Basics, Recent Advances, and Future Trends