当前位置: X-MOL 学术Displays › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
DLSE-Net: A robust weakly supervised network for fabric defect detection
Displays ( IF 4.3 ) Pub Date : 2021-05-01 , DOI: 10.1016/j.displa.2021.102008
Zhoufeng Liu , Zhaochen Huo , Chunlei Li , Yan Dong , Bicao Li

The feasibility of deep convolutional neural network for fabric defect detection has been proven, but the detection performance often depends on large-scale labeled datasets. However, it is troublesome to collect large amounts of fabric defects with pixel-level labeling in industrial production. Although the weakly supervised detection methods can reduce the labeling workload, fabric defect detection is still a challenging task due to the slight difference between defects and complex texture backgrounds, and the diversity of defect types. To alleviate this issue, this paper proposes an effective weakly supervised shallow network, called DLSE-Net, with Link-SE (L-SE) module and Dilation Up-Weight CAM (DUW-CAM) for fabric defect detection. Firstly, the network regards a residual connection as a new branch to alleviate the semantic gap generated by the connection of different layers. Secondly, L-SE module forces the weights to be associated with the overall network in a global optimization manner instead of only within a single layer. Finally, a novel DUW-CAM with an attention mechanism is proposed to improve the adaptability of the network by combining dilated convolution and attention mechanism. Moreover, DUW-CAM can effectively suppress the background and highlight defect regions, even on complex fabric textures. Experimental results demonstrate that our proposed approach can localize the defects with high accuracy, and outperforms the state-of-the-art methods on two distinctive fabric datasets with different textures.



中文翻译:

DLSE-Net:健壮的弱监督网络,用于结构缺陷检测

深度卷积神经网络用于织物缺陷检测的可行性已得到证明,但检测性能通常取决于大规模的标记数据集。但是,在工业生产中用像素级标记收集大量织物缺陷是很麻烦的。尽管监督不力的检测方法可以减少标记工作量,但由于缺陷与复杂纹理背景之间的细微差异以及缺陷类型的多样性,织物缺陷检测仍然是一项艰巨的任务。为了缓解这个问题,本文提出了一种有效的弱监督浅层网络,称为DLSE-Net,该网络具有Link-SE(L-SE)模块和Diation Up-Weight CAM(DUW-CAM)用于织物缺陷检测。首先,网络将残余连接视为新的分支,以减轻由不同层的连接产生的语义鸿沟。其次,L-SE模块强制权重以全局优化方式而不是仅在单个层内与整个网络相关联。最后,提出了一种新型的具有注意力机制的DUW-CAM,通过结合扩张卷积和注意力机制来提高网络的适应性。而且,即使在复杂的织物质地上,DUW-CAM也可以有效地抑制背景并突出缺陷区域。实验结果表明,我们提出的方法可以高精度地定位缺陷,并且在两个具有不同纹理的独特织物数据集上优于最新方法。L-SE模块强制权重以全局优化方式而不是仅在单个层内与整个网络相关联。最后,提出了一种新型的具有注意力机制的DUW-CAM,通过结合扩张卷积和注意力机制来提高网络的适应性。而且,即使在复杂的织物质地上,DUW-CAM也可以有效地抑制背景并突出缺陷区域。实验结果表明,我们提出的方法可以高精度地定位缺陷,并且在两个具有不同纹理的独特织物数据集上优于最新方法。L-SE模块强制权重以全局优化方式而不是仅在单个层内与整个网络相关联。最后,提出了一种新型的具有注意力机制的DUW-CAM,通过结合扩张卷积和注意力机制来提高网络的适应性。而且,即使在复杂的织物质地上,DUW-CAM也可以有效地抑制背景并突出缺陷区域。实验结果表明,我们提出的方法可以高精度地定位缺陷,并且在两个具有不同纹理的独特织物数据集上优于最新方法。提出了一种新型的具有注意力机制的DUW-CAM,通过结合扩张卷积和注意力机制来提高网络的适应性。而且,即使在复杂的织物质地上,DUW-CAM也可以有效地抑制背景并突出缺陷区域。实验结果表明,我们提出的方法可以高精度地定位缺陷,并且在两个具有不同纹理的独特织物数据集上优于最新方法。提出了一种新型的具有注意力机制的DUW-CAM,通过结合扩张卷积和注意力机制来提高网络的适应性。而且,即使在复杂的织物质地上,DUW-CAM也可以有效地抑制背景并突出缺陷区域。实验结果表明,我们提出的方法可以高精度地定位缺陷,并且在两个具有不同纹理的独特织物数据集上优于最新方法。

更新日期:2021-05-05
down
wechat
bug