# 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)。

Repository: https://github.com/M-3LAB/awesome-industrial-anomaly-detection
Canonical: https://ross.abutalabs.com/products/awesome-industrial-anomaly-detection
Homepage: https://link.springer.com/content/pdf/10.1007/s11633-023-1459-z.pdf
License Family: other
Topics: anomaly-detection, anomaly-segmentation, deep-learning, defect-detection, industrial-image, computer-vision, dataset, medical
Last push: 2026-08-21T07:55:15+00:00

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 35, longevity 97
- inputs: {"age_days": 1370, "days_push": 12, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3747, forks 340 (observed 2026-08-28T04:08:17.604643+00:00)

## What it is
A curated awesome-list of papers, datasets, benchmarks, and SOTA methods for industrial image anomaly and defect detection. It accompanies a published survey and is continuously updated with recent research from major conferences.

## Use cases
- find papers on industrial anomaly detection
- find datasets for defect detection in manufacturing images
- survey state-of-the-art anomaly segmentation methods
- research benchmarks for visual quality inspection
- keep up with anomaly detection papers from CVPR, ECCV, NeurIPS
- compare anomaly synthesis methods for training data

## When to choose
- you need a curated starting point for industrial anomaly detection research
- you want links to datasets like MVTec AD and recent SOTA code
- you are writing a literature review on defect detection

## When to avoid
- you need runnable software rather than a paper list
- you need non-image anomaly detection such as time-series or logs
- you need a maintained library with an API

## Facets
- artifact type: learning-resource
- maturity: active
- function: computer-vision, machine-learning, data-science
- domain: computer-vision, image-processing, artificial-intelligence, deep-learning
- platform: cross-platform
- tags: awesome-list, anomaly-detection, defect-detection, industrial-inspection, paper-list, datasets, survey, manufacturing

## Member repositories
- M-3LAB/awesome-industrial-anomaly-detection (main) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:17.604643+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:29:02.095282+00:00, confidence not recorded.
  - readme: https://github.com/M-3LAB/awesome-industrial-anomaly-detection (fetched 2026-08-28T04:08:17.604643+00:00, sha 692ca01a01e5)
- Data as of 2026-08-30T08:39:29.467469+00:00.