This is the official implementation of the paper CANet: Contextual information and spatial attention based network for detecting small defects in manufacturing industry accepeted to journal Pattern Recognition. Author: Xiuquan Hou, Meiqin Liu, Senlin Zhang, Ping Wei, Badong Chen.

💖 If our CANet is helpful to your researches or projects, please help star this repository. Thanks! 🤗

We provide two implementations based on MMDetection and PyTorch. For better scalability and simpler environment configuration, I will mainly maintain the implementation based on pure PyTorch, which is more recommended to use.

• CANet based on MMDetection
• CANet based on pure PyTorch

• [2024.7.5] Add the implementation of CANet based on pure PyTorch.
• [2023.3.27] Paper is accepted to Pattern Recognition, code is available.

If you find our work helpful for your research, please consider citing the following BibTeX entry or give us a star ⭐.

@article{HOU2023109558,
    title = {CANet: Contextual Information and Spatial Attention Based Network for Detecting Small Defects in Manufacturing Industry},
    journal = {Pattern Recognition},
    volume = {140},
    pages = {109558},
    year = {2023},
    issn = {0031-3203},
    doi = {https://doi.org/10.1016/j.patcog.2023.109558},
    url = {https://www.sciencedirect.com/science/article/pii/S0031320323002583},
    author = {Xiuquan Hou and Meiqin Liu and Senlin Zhang and Ping Wei and Badong Chen},
}