Skip to main content
Context Awesome

awesome-industrial-anomaly-detection

github.com/m-3lab/awesome-industrial-anomaly-detection ↗

Paper list and datasets for industrial image anomaly/defect detection (updating). 工业异常/瑕疵检测论文及数据集检索库(持续更新)。

3.6k
GitHub Stars
676
Curated Resources
22
Categories
22 hours ago
Last Refreshed
ICML 2026CVPR 2026ICLR 2026AAAI 2026NeurIPS 2025KDD 2025ICCV 2025ICML 2025CVPR 20252.1 Feature-Embedding-based Methods2.2 Reconstruction-Based Methods2.3 Supervised AD3.1 Zero/Few-Shot AD3.2 Noisy AD3.3 Anomaly Synthesis [awesome-anomaly-synthesis]3.4 RGBD AD3.5 3D AD3.6 Continual AD3.7 Uniform/Multi-Class AD3.8 Logical AD3.9 MLLM-based ADOther settings

Use this list with your AI agent

Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:

"Show me universal task resources from awesome-industrial-anomaly-detection"

Installation instructions →

What's inside

Other settings

2.2 Reconstruction-Based Methods

2.3 Supervised AD

  • [2018]More Abnormal Samples

  • [2021]More Abnormal Samples

  • [2021]More Normal Samples With (Less Abnormal Samples or Weak Labels)

  • [2022]More Abnormal Samples

  • [2023]More Normal Samples With (Less Abnormal Samples or Weak Labels)

  • [2023]More Abnormal Samples

3.3 Anomaly Synthesis [awesome-anomaly-synthesis]

2.1 Feature-Embedding-based Methods

  • [2020]2.1.2 One-Class Classification (OCC)

  • [2020]2.1.4 Memory Bank

  • [2020]2.1.2 One-Class Classification (OCC)

  • [2021]2.1.3 Distribution-Map

  • [2021]2.1.3 Distribution-Map

  • [2021]2.1.4 Memory Bank

3.1 Zero/Few-Shot AD

Showing a sample of 676 resources. View the full list on GitHub →