memseg's Introduction

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

notebook
Describable Textures Dataset(DTD) [ download ]

2. Model Process

notebook

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	98.31	99.05
pill	96.21	88	90.23
carpet	98.72	94.1	95.31
hazelnut	97.89	89.28	94.86
tile	100	98.97	98.84
cable	83.71	74.69	73.21
toothbrush	100	98.67	97.13
transistor	92.42	75	79.41
zipper	99.63	93.94	93
metal_nut	90.42	80.99	90.62
grid	99.92	96.48	95.87
bottle	100	94.67	92.61
capsule	92.34	83.45	84.34
screw	81.64	83.04	82.93
wood	99.74	94.9	94.45
Average	95.51	89.63	90.79

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}
}

Recommend Projects