For the Training Image Labeler, can you include images without the structure-of-interest to improve the RCNN training?

Question

Joseph Stember 2017-8-10

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/352328-for-the-training-image-labeler-can-you-include-images-without-the-structure-of-interest-to-improve

关闭： MATLAB Answer Bot 2021-8-20

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

此问题已关闭。

Answer 1

Nick Choi 2017-8-16

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/352328-for-the-training-image-labeler-can-you-include-images-without-the-structure-of-interest-to-improve#answer_278203

You could provide more images without the structure of interest to the Training Image Labeler but there is no guarantee that it would improve the performance of the RCNN. It depends on the data set but including more images without the structure of interest can have trade offs as mentioned in this doc link: https://www.mathworks.com/help/vision/ug/train-a-cascade-object-detector.html#btu4ez9-1