Towards Open-Vocabulary Industrial Defect Understanding with a Large-Scale Multimodal Dataset
Not on the map. Why?
Abstract (arXiv)
We present IMDD-1M, the first large-scale Industrial Multimodal Defect Dataset comprising 1,000,000 aligned image-text pairs, designed to advance multimodal learning for manufacturing and quality inspection. IMDD-1M contains high-resolution real-world defects spanning over 60 material categories and more than 400 defect types, each accompanied by expert-verified annotations and fine-grained textual descriptions detailing defect location, severity, and contextual attributes. This dataset enables a wide spectrum of applications, including classification, segmentation, retrieval, captioning, and generative modeling. Building upon IMDD-1M, we train a diffusion-based vision-language foundation model from scratch, specifically tailored for industrial scenarios. The model serves as a generalizable foundation that can be efficiently adapted to specialized domains through lightweight fine-tuning. With less than 5% of the task-specific data required by dedicated expert models, it achieves comparable performance, highlighting the potential of data-efficient foundation model adaptation for industrial inspection and generation, paving the way for scalable, domain-adaptive, and knowledge-grounded manufacturing intelligence. Additional details and resources can be found in this URL: https://ninaneon.github.io/projectpage/
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 14 of its 26 references that are in the map. First posted on arXiv 30 Dec 2025.
Builds on
14 of 26 references.
References · 14
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
- 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
- 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
- 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
- 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
- 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 223
- 2019Segmentation-Based Deep-Learning Approach for Surface-Defect Detectioncited by 145
- 2024Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detectioncited by 139
- 2024PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detectioncited by 98
- 2023Anomaly Detection with Conditioned Denoising Diffusion Modelscited by 56
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2026Unification of Closed-Open Industrial Detection Scenarios: New Large-Scale Benchmarks,Challenges and Baselines
- 2026Synthetic Defect Image Generation for Power Line Insulator Inspection Using Multimodal Large Language Models
- 2024FabGPT: An Efficient Large Multimodal Model for Complex Wafer Defect Knowledge Queries
- 2024MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection
- 2026AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparison
- 2026FORGE: Fine-grained Multimodal Evaluation for Manufacturing Scenarios
- 2026GenAU: Language-Grounded Industrial Anomaly Understanding with Vision-Language Models
- 2026Industrial Anomaly Detection via Defect-Grounded Reasoning in Visual Latent Space