You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
在论文中提到的object-to-scene correlation loss如下图所示,P被描述为“the image-level label that notifies which categories appear in the image or which is a zero/one paradigm”,我不太理解这个P的具体细节,是描述一幅图像存在几个类别?还是一幅图像完全像素级别分类?我目前的理解是,如果总任务共3个类别,但一幅图像中只存在2个类别时,该图像对应的image-level是:[[1,0,0],[0,1,0],[0,0,0]],不知道是否正确。希望能得到您的指导,谢谢!
The text was updated successfully, but these errors were encountered:
在论文中提到的object-to-scene correlation loss如下图所示,P被描述为“the image-level label that notifies which categories appear in the image or which is a zero/one paradigm”,我不太理解这个P的具体细节,是描述一幅图像存在几个类别?还是一幅图像完全像素级别分类?我目前的理解是,如果总任务共3个类别,但一幅图像中只存在2个类别时,该图像对应的image-level是:[[1,0,0],[0,1,0],[0,0,0]],不知道是否正确。希望能得到您的指导,谢谢!
The text was updated successfully, but these errors were encountered: