Surface Defect Segmentation Algorithm of Steel Plate Based on Geometric Median Filter Pruning

Problems such as redundancy of detection model parameters make it difficult to apply to factory embedded device applications. This paper focuses on the analysis of different existing deep learning model compression algorithms and proposes a model pruning algorithm based on geometric median filtering...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Frontiers in bioengineering and biotechnology Ročník 10; s. 945248
Hlavní autori: Hao, Zhiqiang, Wang, Zhigang, Bai, Dongxu, Tong, Xiliang
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Switzerland Frontiers Media SA 01.07.2022
Frontiers Media S.A
Predmet:
ISSN:2296-4185, 2296-4185
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Problems such as redundancy of detection model parameters make it difficult to apply to factory embedded device applications. This paper focuses on the analysis of different existing deep learning model compression algorithms and proposes a model pruning algorithm based on geometric median filtering for structured pruning and compression of defect segmentation detection networks on the basis of structured pruning. Through experimental comparisons and optimizations, the proposed optimization algorithm can greatly reduce the network parameters and computational effort to achieve effective pruning of the defect detection algorithm for steel plate surfaces.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
Reviewed by: Guanbing Cheng, Civil Aviation University of China, Tianjin, China
This article was submitted to Bionics and Biomimetics, a section of the journal Frontiers in Bioengineering and Biotechnology
Weichao Guo, Shanghai Jiao Tong University, China
Edited by: Zhihua Cui, Taiyuan University of Science and Technology, China
ISSN:2296-4185
2296-4185
DOI:10.3389/fbioe.2022.945248