跳至主導覽
跳至搜尋
跳過主要內容
國立中央大學 首頁
說明與常見問題
English
中文
首頁
人才檔案
研究單位
研究計畫
研究成果
資料集
榮譽/獲獎
學術活動
新聞/媒體
影響
按專業知識、姓名或所屬機構搜尋
PreAugNet: improve data augmentation for industrial defect classification with small-scale training data
Isack Farady,
Chih Yang Lin
, Ming Ching Chang
機械工程學系
研究成果
:
雜誌貢獻
›
期刊論文
›
同行評審
16
引文 斯高帕斯（Scopus）
總覽
指紋
指紋
深入研究「PreAugNet: improve data augmentation for industrial defect classification with small-scale training data」主題。共同形成了獨特的指紋。
排序方式
重量
按字母排序
Keyphrases
Training Data
100%
Defect Classification
100%
Data Augmentation
100%
Training Samples
75%
Target Network
50%
Network Architecture
25%
Support Vector Machine Classifier
25%
Decision Boundary
25%
Deep Convolutional Neural Network (deep CNN)
25%
Network Data
25%
Class Label
25%
GAINS Model
25%
Deep Learning Neural Network
25%
Training Model
25%
Classification Network
25%
Training Quality
25%
Image Augmentation
25%
Steel Surface Defects
25%
Surface Defect Detection
25%
Steel Surface Defect Detection
25%
Defect Dataset
25%
Steel Defects
25%
High-quality Sample
25%
Synthetic Data Augmentation
25%
Classification Boundary
25%
Independent Support
25%
Engineering
Defect Classification
100%
Target Network
100%
Steel Surface
100%
Surface Defect
100%
Classification Network
50%
Decision Boundary
50%
Class Label
50%
Deep Learning Method
50%
Convolutional Neural Network
50%
Support Vector Machine
50%
Computer Science
Training Data
100%
Data Augmentation
100%
Training Sample
60%
Large Data Set
20%
Support Vector Machine
20%
Network Architecture
20%
Decision Boundary
20%
Training Model
20%
Network Target
20%
Convolutional Neural Network
20%
Synthetic Data
20%
Boundary Classifier
20%
Independent Support
20%
Deep Learning Method
20%
Chemical Engineering
Neural Network
100%
Deep Learning Method
100%
Support Vector Machine
100%
Material Science
Surface Defect
100%