Title
Dynamic sample selection method based on classification prediction
Abstract
Recent research has shown that sample selection in the training phase is crucial for improving the accuracy of object detection. For a long time, we always use manually designed IoU threshold to filter out low-quality candidates, but recently some work shows that dynamic sample selection is better for training an object detector. In our paper, we present a new adaptive dynamic sample selection str...
Year
DOI
Venue
2021
10.1109/ICCE-TW52618.2021.9603169
2021 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW)
Keywords
DocType
ISBN
Training,Conferences,Object detection,Detectors,Testing
Conference
978-1-6654-3328-0
Citations 
PageRank 
References 
0
0.34
0
Authors
2
Name
Order
Citations
PageRank
Xing-Fu Wang100.34
Peng-Fei Xie200.34