RepVgg-Tree: a multi-branch tree based parametric reconstruction network for tiny steel surface-defect detection

被引：0

作者：

Zhu L. ^{[1
]}

Jian Y. ^{[1
]}

Wang L. ^{[1
,2
]}

Jia C. ^{[1
]}

Ma X. ^{[1
]}

机构：

[1] Liangjiang International College, Chongqing University of Technology, Banan, Chongqing

[2] Chongqing Jialing Special Equipment Co., Ltd., Chongqing

来源：

International Journal of Wireless and Mobile Computing | 2023年 / 24卷 / 3-4期

关键词：

attention mechanism; defect detection; Double-Tree; RepVgg-Tree; tiny defect;

D O I：

10.1504/ijwmc.2023.131323

中图分类号：

学科分类号：

摘要：

The surface defect detection of steel plates is an essential quality control process in digital manufacturing factories today. Traditional inspection technologies based on image processing are challenging to give a complete solution of tiny defect scale and time-consuming. We propose a novel convolutional neural network with multi-branch tree architecture, of which RepVgg-Tree can be used to realise the decoupling of training-time and inference-time architecture through structure reparameterisation. Each branch has a Vgg-like inference-time body, while the training-time model has a multi-branch topology. Furthermore, the Double-Tree attention mechanism is utilised to local feature position, improve the model's expression ability and reduce information loss. Also, the generalised focal loss is introduced to deal with the imbalance problem of positive samples and negative ones. Meanwhile, experimental results show that our model achieves satisfactory AP and average accuracy performance 95.85% and 95.96% respectively, effectively detecting tiny steel surface defects on the NEU data set. © 2023 Inderscience Enterprises Ltd.

引用

页码：329 / 340

页数：11

共 29 条

[1]

Bochkovskiy A., Wang C-Y., YOLOv4: Hong-Yuan Mark Liao optimal speed and accuracy of object detection, (2004)

[2]

Chu H.H., Wang Z.Y., A vision-based system for postwelding quality measurement and defect detection, The International Journal of Advanced Manufacturing Technology, 86, 9, pp. 3007-3014, (2016)

[3]

Ding X., Guo Y., Ding G., Han J., Acnet: strengthening the kernel skeletons for powerful CNN via asymmetric convolution blocks, Proceedings of the IEEE International Conference on Computer Vision, pp. 1911-1920, (2019)

[4]

Ding X., Zhang X., Ma N., Han J., Ding G., Sun J., RepVGG: making VGG-style ConvNets great again, Proceedings of the IEEE international Conference on Computer Vision, pp. 1440-1448, (2022)

[5]

Guo S., Alvarez J.M., Salzmann M., Expandnets: linear over-parameterization to train compact convolutional networks, Advances in Neural Information Processing Systems, 33, 3, (2020)

[6]

Guo T., Zhang L., Ding R., Yang G., EDD-Net: an efficient defect detection network, Proceedings of the International Conference on Pattern Recognition, pp. 8899-8905, (2021)

[7]

Han K., Wang Y., Tian Q., Et al., GhostNet: more features from cheap operations, Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1580-1589, (2020)

[8]

He K., Gkioxari G., Dollar P., Girshick R., Mask-RCNN

[9]

He K., Zhang X., Ren S., Sun J., Deep residual learning for image recognition, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770-778, (2016)

[10]

He Y., Song K.C., Meng Q.G., Yan Y.H., An end-toend steel surface defect detection approach via fusing multiple hierarchical features, IEEE Transactions on Instrumentation and Measurement, 69, 4, pp. 1493-1504, (2020)

← 1 2 3 →