coco_loss
coco_loss copied to clipboard
Implement for ``Learning Deep Features via Congenerous Cosine Loss for Person Recognition''
Besides your 99.78% on lfw and 76.57% on megaface, I was also very curious about your baseline method. Training on casia, softmax can get 99.5% on lfw, only using resnet...
Would it be any training code for COCO loss available soon? Will you provide trained models for other tasks such as person recognition or face recognition? Thanks
your coco_loss,centerloss ;Can they be used for facial feature extraction? Do I need to increase the number of network layers?
In your paper, it's said that the centroid of class as average of features over a mini-batch which implies you update the centroid during training according to different mini-batches. But...
Thanks for the great idea of using classification layer for cosine distance computation! Could you please elaborate on how you train that layer? As I understand you initialize weights with...