AMFF-YOLOX: Towards an Attention Mechanism and Multiple Feature Fusion Based on YOLOX for Industrial Defect Detection

Authors:
Open Access
Publisher website
Google Scholar
Abstract
Industrial defect detection has great significance in product quality improvement, and deep learning methods are now the dominant approach. However, the volume of industrial products is enormous and mainstream detectors are unable to maintain a high accuracy rate during rapid detection. To address the above issues, this paper proposes AMFF-YOLOX, an improved industrial defect detector based on YOLOX. The proposed method can reduce the activation function and normalization operation of the bottleneck in the backbone network, and add an attention mechanism and adaptive spatial feature fusion within the feature extraction network to enable the network to better focus on the object. Ultimately, the accuracy of the prediction is enhanced without excessive loss of speed in network prediction, with competitive performance compared to mainstream detectors. Experiments show that the proposed method in this paper achieves 61.06% (85.00%) mAP@0.5:0.95 (mAP@0.5) in the NRSD-MN dataset, 51.58% (91.09%) is achieved in the PCB dataset, and 49.08% (80.48%) is achieved in the NEU-DET dataset. A large number of comparison and ablation experiments validate the effectiveness and competitiveness of the model in industrial defect detection scenarios.
Funding Information
  • Shandong Provincial Natural Science Foundation, China (ZR2022MF279, 2019JZZY020113, TC200802C, 2021TSGC1089, 2021GXRC074)
  • Key R&D project of Shandong Province of China (ZR2022MF279, 2019JZZY020113, TC200802C, 2021TSGC1089, 2021GXRC074)
  • 2020 Industrial Internet Innovation and Development Project (ZR2022MF279, 2019JZZY020113, TC200802C, 2021TSGC1089, 2021GXRC074)
  • Science and Technology SMEs Innovation Capacity Enhancement Project in Shandong Province (ZR2022MF279, 2019JZZY020113, TC200802C, 2021TSGC1089, 2021GXRC074)
  • “20 New Colleges and Universities” Funding Project in Jinan (ZR2022MF279, 2019JZZY020113, TC200802C, 2021TSGC1089, 2021GXRC074)

This publication has 42 references indexed in Scilit: