Deep Active Learning for Surface Defect Detection
Most of the current object detection approaches deliver competitive results with an assumption that a large number of labeled data are generally available and can be fed into a deep network at once. However, due to expensive labeling efforts, it is difficult to deploy the object detection systems in...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/6/1650 |
| _version_ | 1828116965378490368 |
|---|---|
| author | Xiaoming Lv Fajie Duan Jia-Jia Jiang Xiao Fu Lin Gan |
| author_facet | Xiaoming Lv Fajie Duan Jia-Jia Jiang Xiao Fu Lin Gan |
| author_sort | Xiaoming Lv |
| collection | DOAJ |
| description | Most of the current object detection approaches deliver competitive results with an assumption that a large number of labeled data are generally available and can be fed into a deep network at once. However, due to expensive labeling efforts, it is difficult to deploy the object detection systems into more complex and challenging real-world environments, especially for defect detection in real industries. In order to reduce the labeling efforts, this study proposes an active learning framework for defect detection. First, an Uncertainty Sampling is proposed to produce the candidate list for annotation. Uncertain images can provide more informative knowledge for the learning process. Then, an Average Margin method is designed to set the sampling scale for each defect category. In addition, an iterative pattern of training and selection is adopted to train an effective detection model. Extensive experiments demonstrate that the proposed method can render the required performance with fewer labeled data. |
| first_indexed | 2024-04-11T13:06:32Z |
| format | Article |
| id | doaj.art-dea951ddfb374b8c9fc172c4081f22dc |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T13:06:32Z |
| publishDate | 2020-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-dea951ddfb374b8c9fc172c4081f22dc2022-12-22T04:22:45ZengMDPI AGSensors1424-82202020-03-01206165010.3390/s20061650s20061650Deep Active Learning for Surface Defect DetectionXiaoming Lv0Fajie Duan1Jia-Jia Jiang2Xiao Fu3Lin Gan4The State Key Lab of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 300072, ChinaThe State Key Lab of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 300072, ChinaThe State Key Lab of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 300072, ChinaThe State Key Lab of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 300072, ChinaThe State Key Lab of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 300072, ChinaMost of the current object detection approaches deliver competitive results with an assumption that a large number of labeled data are generally available and can be fed into a deep network at once. However, due to expensive labeling efforts, it is difficult to deploy the object detection systems into more complex and challenging real-world environments, especially for defect detection in real industries. In order to reduce the labeling efforts, this study proposes an active learning framework for defect detection. First, an Uncertainty Sampling is proposed to produce the candidate list for annotation. Uncertain images can provide more informative knowledge for the learning process. Then, an Average Margin method is designed to set the sampling scale for each defect category. In addition, an iterative pattern of training and selection is adopted to train an effective detection model. Extensive experiments demonstrate that the proposed method can render the required performance with fewer labeled data.https://www.mdpi.com/1424-8220/20/6/1650surface defect detectionactive learningdeep learning |
| spellingShingle | Xiaoming Lv Fajie Duan Jia-Jia Jiang Xiao Fu Lin Gan Deep Active Learning for Surface Defect Detection Sensors surface defect detection active learning deep learning |
| title | Deep Active Learning for Surface Defect Detection |
| title_full | Deep Active Learning for Surface Defect Detection |
| title_fullStr | Deep Active Learning for Surface Defect Detection |
| title_full_unstemmed | Deep Active Learning for Surface Defect Detection |
| title_short | Deep Active Learning for Surface Defect Detection |
| title_sort | deep active learning for surface defect detection |
| topic | surface defect detection active learning deep learning |
| url | https://www.mdpi.com/1424-8220/20/6/1650 |
| work_keys_str_mv | AT xiaominglv deepactivelearningforsurfacedefectdetection AT fajieduan deepactivelearningforsurfacedefectdetection AT jiajiajiang deepactivelearningforsurfacedefectdetection AT xiaofu deepactivelearningforsurfacedefectdetection AT lingan deepactivelearningforsurfacedefectdetection |