Jia Guo

Tripletloss(Facenet) for few shot learning

7

For few-shot learning tasks like IDCardCamera face verification(identification), we only have two face images for each person in most cases for training. Under such situation, metric learning approaches can be...

Common Resnet gives bad result.

1

Hi authors, I have tried your network structure with sphere loss and it can give similar result which mentioned in your paper. However, when I switched to use common resnet-50...

Why number of labels has to be greater than 2 in MultiBoxTarget?

4

I saw one piece of code in MultiBoxTarget.cu below: ``` const int num_labels = labels.size(1); CHECK_GT(num_labels, 2); ``` But why? I think one or two ground truth boxes are also...

Any plan to support on-GPU augmentations?

1

Hello, is there any plan to support on-devices(GPU) augmentations? It will be quite useful to boost the performance on multi-GPUs servers.

[MFR21] ICCV21 masked face recognition challenge discussion

105

How to participate: [https://github.com/deepinsight/insightface/tree/master/challenges/iccv21-mfr](https://github.com/deepinsight/insightface/tree/master/challenges/iccv21-mfr) Submission server: http://iccv21-mfr.com/ Workshop homepage: https://ibug.doc.ic.ac.uk/resources/masked-face-recognition-challenge-workshop-iccv-21/ Any issue can be left in this thread.

Thanks!