CPAM: Cross Patch Attention Module for Complex Texture Tile Block Defect Detection
Source abstract
Abstract
Due to the little variation in defect points, tile block defect detection typically detects subtle defects in large-format images, allowing defective characteristics to be displayed regionally. Traditional convolutional neural network architectures that extract regional features take into account the connection between regional features simply, resulting in the presence of region-specific bias, which makes tile block defect detection still a challenging task. To address this challenge, this paper divides feature information into patches that can represent different regional features. Additionally, the relationship between different patches and tile block defects is studied; as a result, this paper proposes a new attention mechanism called the Cross Patch Attention Module (CPAM). Since the regional performance of patches is consistent with the tile block defect characteristics, CPAM can distinguish various regional features by patches. Then, in order to create reliable one-dimensional patch information, CPAM provides a method to connect patches linearly in two spatial directions. This takes into account the correlation of adjacent patches in various spatial directions. Finally, by extracting the regional characteristics of patches, CPAM can successfully assist the model in distinguishing the importance of different patches. The experimental results demonstrate that CPAM has excellent performance for tile block defect detection, and plugging CPAM into different end-to-end models can have a good gain effect, which can effectively and stably help the model to complete the task of tile block defect detection.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Integrated Circuits and Semiconductor Failure Analysis · Advanced Neural Network Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Mechatronic Engineering and Automation, Foshan University, Foshan 528225, China
Department of Industrial Engineering and Engineering Management, National Tsing Hua University, Hsinchu 30013, Taiwan
Funding
Guangdong Province Key Field R&D Program Project · National Natural Science Foundation of China · Foshan City Key Field Science and Technology Research Project · Shunde District Core Technology Research Project
References (30)
Show source-provided references
1. Classification of biscuit tiles for defect detection using Fourier transform features10.1016/j.isatra.2021.06.025 ↗
2. Zhou, H., Jang, B., Chen, Y., and Troendle, D. (2020, January 21–23). Exploring faster RCNN for fabric defect detection. Proceedings of the 2020 Third International Conference on Artificial Intelligence for Industries (AI4I), Irvine, CA, USA.10.1109/AI4I49448.2020.00018 ↗
3. Feng, Z., Guo, L., Huang, D., and Li, R. (2021, January 14–16). Electrical insulator defects detection method based on yolov5. Proceedings of the 2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS), Suzhou, China.10.1109/DDCLS52934.2021.9455519 ↗
4. Improved YOLOV4-CSP Algorithm for Detection of Bamboo Surface Sliver Defects With Extreme Aspect Ratio10.1109/ACCESS.2022.3152552 ↗
5. Rahaman, G., and Hossain, M. (2009). Automatic defect detection and classification technique from image: A special case using ceramic tiles. arXiv.
6. Surface defect detection in tiling Industries using digital image processing methods: Analysis and evaluation10.1016/j.isatra.2013.11.015 ↗
7. Automatic detection and classification of the ceramic tiles’ surface defects10.1016/j.patcog.2016.11.021 ↗
8. Automated visual defect detection for flat steel surface: A survey10.1109/TIM.2019.2963555 ↗
9. Ceramic tile surface defect detection based on deep learning10.1016/j.ceramint.2021.12.328 ↗
10. Skin lesion classification using CNNs with patch-based attention and diagnosis-guided loss weighting10.1109/TBME.2019.2915839 ↗
11. FFCNN: A deep neural network for surface defect detection of magnetic tile10.1109/TIE.2020.2982115 ↗
12. Tile damage detection in temple facade via convolutional neural networks
13. Stephen, O., Maduh, U.J., and Sain, M. (2021). A machine learning method for detection of surface defects on ceramic tiles using convolutional neural networks. Electronics, 11.10.3390/electronics11010055 ↗
14. Woo, S., Park, J., Lee, J.Y., and Kweon, I.S. (2018, January 8–14). Cbam: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01234-2_1 ↗
15. A two-stage multiscale residual attention network for light guide plate defect detection10.1109/ACCESS.2020.3047221 ↗
16. RetinaNet with difference channel attention and adaptively spatial feature fusion for steel surface defect detection
17. Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., and Hu, Q. (2020, January 13–19). ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.01155 ↗
18. Transformer in transformer
19. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An image is worth 16 × 16 words: Transformers for image recognition at scale. arXiv.
20. Cordonnier, J.B., Loukas, A., and Jaggi, M. (2019). On the relationship between self-attention and convolutional layers. arXiv.
21. Mlp-mixer: An all-mlp architecture for vision
22. Van Etten, A. (2018). You only look twice: Rapid multi-scale object detection in satellite imagery. arXiv.
23. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016, January 11–14). Ssd: Single shot multibox detector. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46448-0_2 ↗
24. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.C. (2018, January 18–23). Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00474 ↗
25. Bochkovskiy, A., Wang, C.Y., and Liao, H.Y.M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv.
26. Jocher, G., Chaurasia, A., Stoken, A., Borovec, J., NanoCode012, Kwon, Y., Xie, T., Michael, K., Fang, J., and imyhxy (2022). ultralytics/yolov5: V6.2—YOLOv5 Classification Models, Apple M1, Reproducibility, ClearML and Deci.ai integrations, Zenodo.
27. Ge, Z., Liu, S., Wang, F., Li, Z., and Sun, J. (2021). Yolox: Exceeding yolo series in 2021. arXiv.
28. Wang, C.Y., Bochkovskiy, A., and Liao, H.Y.M. (2022). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv.10.1109/CVPR52729.2023.00721 ↗
29. Hu, J., Shen, L., and Sun, G. (2018, January 18–23). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00745 ↗
30. Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22–29). Grad-cam: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.74 ↗