Shi Chenbo, Wang Kang, Zhang Guodong, Li Zelong, Zhu Changsheng
College of Intelligent Equipment, Shandong University of Science and Technology, Taian, 271019, China.
Department of Artificial Intelligence, Suzhou Lamberv Intelligent Technology, Suzhou, 215000, China.
Sci Rep. 2024 Sep 19;14(1):21874. doi: 10.1038/s41598-024-72579-6.
Deep learning-based defect detection methods have gained widespread application in industrial quality inspection. However, limitations such as insufficient sample sizes, low data utilization, and issues with accuracy and speed persist. This paper proposes a semi-supervised semantic segmentation framework that addresses these challenges through perturbation invariance at both the image and feature space. The framework employs diverse perturbation cross-pseudo-supervision to reduce dependency on extensive labeled datasets. Our lightweight method incorporates edge pixel-level semantic information and shallow feature fusion to enhance real-time performance and improve the accuracy of defect edge detection and small target segmentation in industrial inspection. Experimental results demonstrate that the proposed method outperforms the current state-of-the-art (SOTA) semi-supervised semantic segmentation methods across various industrial scenarios. Specifically, our method achieves a mean Intersection over Union (mIoU) 3.11% higher than the SOTA method on our dataset and 4.39% higher on the public KolektorSDD dataset. Additionally, our semantic segmentation network matches the speed of the fastest network, U-net, while achieving a mIoU 2.99% higher than DeepLabv3Plus.
基于深度学习的缺陷检测方法在工业质量检测中得到了广泛应用。然而，诸如样本量不足、数据利用率低以及准确性和速度方面的问题仍然存在。本文提出了一种半监督语义分割框架，该框架通过图像和特征空间的扰动不变性来应对这些挑战。该框架采用多样的扰动交叉伪监督来减少对大量标注数据集的依赖。我们的轻量级方法结合了边缘像素级语义信息和浅层特征融合，以提高实时性能，并提高工业检测中缺陷边缘检测和小目标分割的准确性。实验结果表明，在各种工业场景中，所提出的方法优于当前的最新（SOTA）半监督语义分割方法。具体而言，我们的方法在我们的数据集上比SOTA方法的平均交并比（mIoU）高3.11%，在公共KolektorSDD数据集上高4.39%。此外，我们的语义分割网络与最快的网络U-net速度相当，同时mIoU比DeepLabv3Plus高2.99%。
