Open AccessUsing Darts to Improve Mold ID Recognition Model Based on MASK R-CNN
Author(s) -
Wa He,
Yuting Wu,
Liang Peng,
Gang Hao
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1518/1/012042
Subject(s) - task (project management) , computer science , artificial intelligence , segmentation , pattern recognition (psychology) , mold , transfer of learning , network model , image (mathematics) , machine learning , engineering , systems engineering , biology , genetics
Mask R-CNN model is an excellent image segmentation model, but cannot perform well on the task of mold ID recognition. To address the aboved problem, this paper improves the classification branch of Mask R-CNN model by applying DARTs, making the improved classification branch more suitable for mold ID recognition task. Firstly, DARTs is employed to obtain network cell structure. Secondly, the network cell structure is used to improve the classification branch. Moreover, we make the model converge under 2GPU days based on transfer learning. Finally, the experimental results show that the improved model can achieve higher accuracy with IOU of 0.5 (increased by 1.02%) and 0.75 (increased by 2.42%).