backseason
commented
3 years ago I can not give you much useful suggestions as I have not tried this kind of data augmentation in SOD. But you may refer to the image matting papers.
kobe notifications@github.com 于2021年1月27日周三 下午6:02写道：
When I was learning about Salient Object Detection，I used composite images to augment the training set： C= F × α + B × (1 − α i ) C：composite image F： foreground image B: background image α values the image mask. After the completion of training, the final effect does not reach the expectation, and some results often appear low gray value of the shadow.Regarding this phenomenon, do you have any suggestions for setting alpha or image mask. Looking forward to your reply
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/backseason/PoolNet/issues/75, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABYO2OASPF26QCYGIHY2TMTS37QFFANCNFSM4WU7DHHA .
--
From BackSeason-刘姜江 Major in Computer Science and Technology Nankai University, Tianjin,300350 P.R.China J04.liu@gmail.com j04.liu@gmail.com
When I was learning about Salient Object Detection，I used composite images to augment the training set： C= F × α + B × (1 − α)
C：composite image F： foreground image B: background image α values the image mask. After the completion of training, the final effect does not reach the expectation, and some results often appear low gray value of the shadow.Regarding this phenomenon, do you have any suggestions for setting alpha or image mask. Looking forward to your reply