https://github.com/shinmura0/autoencoder_vs_metriclearning
AutoEncoder vs Metric Learning for Anomaly Detection
https://github.com/shinmura0/autoencoder_vs_metriclearning
anomaly-detection deep-learning keras machine-learning
Last synced: 4 months ago
JSON representation
AutoEncoder vs Metric Learning for Anomaly Detection
- Host: GitHub
- URL: https://github.com/shinmura0/autoencoder_vs_metriclearning
- Owner: shinmura0
- License: mit
- Created: 2019-09-02T22:16:57.000Z (almost 7 years ago)
- Default Branch: master
- Last Pushed: 2020-01-08T03:35:44.000Z (over 6 years ago)
- Last Synced: 2025-07-13T15:18:11.090Z (12 months ago)
- Topics: anomaly-detection, deep-learning, keras, machine-learning
- Language: Jupyter Notebook
- Size: 11.7 MB
- Stars: 28
- Watchers: 2
- Forks: 4
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# 1.AutoEncoder_vs_MetricLearning
+ AutoEncoder vs Metric Learning for Anomaly Detection
+ Dataset:[MVTEC-AD](https://www.mvtec.com/company/research/datasets/mvtec-ad/)
Click [here](https://qiita.com/shinmura0/items/5c728da8a74208c1308f) for details(Japanese).
# 2.Simple method
|Picture|L2-SoftmaxLoss(AUC)|Simple method(AUC)|
|---|---|---|
|Cable|0.72|0.91|
|Leather|0.91|0.99|
|Carpet|0.71|0.8|
|Capsule|0.57|0.87|
Click [here](https://qiita.com/shinmura0/items/6c805498c390d5b35714) for details(Japanese).
# 3.Self Supervised(class3)


Click [here](https://qiita.com/shinmura0/items/54585fccbb20cb2879fd) for details(Japanese).