Pixel-wise segmentation techniques based on deep learning have been widely applied in the inspection of product surface defects to ensure product quality.However,existing models based on deep learning primarily focus ...Pixel-wise segmentation techniques based on deep learning have been widely applied in the inspection of product surface defects to ensure product quality.However,existing models based on deep learning primarily focus on separate specific defect types,which introduces challenges in generalizing them to the detection of diverse product defects.The relatively low occurrence probability of certain defects also sets obstacles in obtaining sufficient defect samples for effective model training.Herein,an innovative dual-branch edge-based graph reasoning network(DEGRNet)is demonstrated for the few-shot segmentation(FSS)of industrial surface defects,which can be easily generalized to various defects with minimal labeled defect samples.DEGRNet mainly consists of a background eliminating(BE)module,an edge reinforcement(ER)module,and a graph reasoning module.The BE module can effectively fuse the feature information from the support image and support mask to reduce background interference,while the ER module works to accurately extract edge contour information.The rough segmentation maps from BE and the boundary-enhanced segmentation maps from ER are simultaneously input into the dual-branch graph reasoning module to enhance the modeling capability of long-distance feature information and refine segmentation boundaries.This feature enables our model to fully utilize global image features and gain robust generalization capabilities for unknown defect types.The results of multiple experiments validate the effectiveness of the asproposed modules.Our model achieves state-of-the-art performance metrics in few-shot defect segmentations.Specifically,our model exhibits 2.61% and 3.50% improvements in mean intersection over union under the-shot and-shot conditions,respectively,compared with existing state-of-the-art FSS models.展开更多
基金the projects supported by the National Natural Science Foundation of China(Grant No.52305623)Natural Science Foundation of Wuhan,China(Grant No.2024040801020282)Fundamental Research Funds for the Central Universities,China University of Geosciences(Wuhan)(Grant No.120-162301212389).
文摘Pixel-wise segmentation techniques based on deep learning have been widely applied in the inspection of product surface defects to ensure product quality.However,existing models based on deep learning primarily focus on separate specific defect types,which introduces challenges in generalizing them to the detection of diverse product defects.The relatively low occurrence probability of certain defects also sets obstacles in obtaining sufficient defect samples for effective model training.Herein,an innovative dual-branch edge-based graph reasoning network(DEGRNet)is demonstrated for the few-shot segmentation(FSS)of industrial surface defects,which can be easily generalized to various defects with minimal labeled defect samples.DEGRNet mainly consists of a background eliminating(BE)module,an edge reinforcement(ER)module,and a graph reasoning module.The BE module can effectively fuse the feature information from the support image and support mask to reduce background interference,while the ER module works to accurately extract edge contour information.The rough segmentation maps from BE and the boundary-enhanced segmentation maps from ER are simultaneously input into the dual-branch graph reasoning module to enhance the modeling capability of long-distance feature information and refine segmentation boundaries.This feature enables our model to fully utilize global image features and gain robust generalization capabilities for unknown defect types.The results of multiple experiments validate the effectiveness of the asproposed modules.Our model achieves state-of-the-art performance metrics in few-shot defect segmentations.Specifically,our model exhibits 2.61% and 3.50% improvements in mean intersection over union under the-shot and-shot conditions,respectively,compared with existing state-of-the-art FSS models.
