search

anson0910 / CNN_face_detection

Implementation based on the paper Li et al., “A Convolutional Neural Network Cascade for Face Detection, ” 2015 CVPR
253 stars 148 forks source link

about the negative data #2

Closed tangyudi closed 8 years ago

tangyudi commented 8 years ago

sorry to trouble,why train the 24 and 48 detect net should use the negative data from the former detect net(the rectangles from the former result) ,not the negative data same as 12 directly?

anson0910 commented 8 years ago

Hi, according to the paper, since the 12-net is already capable of dropping some negative candidates, the 24 and 48 nets can focus on the candidates that 12-net regard as positive samples. It's some kind of hard negatives data mining.