MemSeg
Unofficial re-implementation for MemSeg: A semi-supervised method for image surface defect detection using differences and commonalities
Environments
- Docker image: nvcr.io/nvidia/pytorch:20.12-py3
einops==0.5.0
timm==0.5.4
wandb==0.12.17
omegaconf
imgaug==0.4.0
Process
1. Anomaly Simulation Strategy
2. Model Process
Run
Example
python main.py configs=configs.yaml DATASET.target=bottle
Demo
voila "[demo] model inference.ipynb" --port ${port} --Voila.ip ${ip}
Results
- Backbone: ResNet18
target | AUROC-image | AUROC-pixel | AUPRO-pixel |
---|---|---|---|
leather | 100 | 99.2 | 99.7 |
pill | 98.83 | 98.26 | 98.49 |
carpet | 99.36 | 97.47 | 97.46 |
hazelnut | 100 | 98.58 | 99.18 |
tile | 100 | 99.53 | 99.47 |
cable | 74.78 | 69.56 | 72.56 |
toothbrush | 100 | 99.55 | 99.11 |
transistor | 94.5 | 84.15 | 87.85 |
zipper | 99.87 | 98.33 | 97.8 |
metal_nut | 99.17 | 95.07 | 97.09 |
grid | 100 | 99.05 | 98.97 |
bottle | 100 | 98.94 | 98.77 |
capsule | 91.74 | 97.26 | 97.1 |
screw | 93.63 | 95.66 | 95.16 |
wood | 99.82 | 96.75 | 98.03 |
Average | 96.78 | 95.16 | 95.78 |
Citation
@article{DBLP:journals/corr/abs-2205-00908,
author = {Minghui Yang and
Peng Wu and
Jing Liu and
Hui Feng},
title = {MemSeg: {A} semi-supervised method for image surface defect detection
using differences and commonalities},
journal = {CoRR},
volume = {abs/2205.00908},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2205.00908},
doi = {10.48550/arXiv.2205.00908},
eprinttype = {arXiv},
eprint = {2205.00908},
timestamp = {Tue, 03 May 2022 15:52:06 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2205-00908.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}