DliHjiang

How to add adapt-mlp to swin-transformer?

14

Thanks for sharing such great work! I have some problem about how to using adapt-mlp in swin? As we know, number channel is different in different stage of swin, so...

when using instance-level self-supervised learning on FPN， do we need to add loss on each level of FPN or still in C5 ?

distance threshold setting when using P3-P6 to do self-supervised learning?

3

when using P3-P6 of FPN to do self-supervised learning, how should we set the distance threshold? Setting it to be 0.7 each level or setting to different value on different...

论文中没有说明multi layer的mimic是怎样进行的，所以我按照rpn分配正样本的规则分配gt到不同的level，即如果一个gt在某个level有正样本，那么该gt就参与生成该level的imitation region，但是实验之后我发现效果很差，蒸馏后的性能比student的baseline还低。请问论文中在进行带fpn的蒸馏实验时是如何分配gt的呢？还是有哪些细节我没有关注到？求解答

I want to train pspnet on my own dataset, but I don't know how to calculate the loss because there are two outputs x and x_aux when training, the x_aux...

caffemodel for VPGNet

4

I have trained a caffemodel from your tutorial, but the test result is bad. I think it is because of little dataset. Could you please tell me where I can...

meets problem when train ssp head

2

Firstly I trained a teacher model and its accuracy is correct, then I train ssp head of teacher model, but I found loss of ssp head falling slowly. the initial...

transferring performance on coco dataset

1

Hello, Have you ever try to transfer the simsiam model to object detection task. I have trained a 200-epoch model on ImageNet through simsiam（following the optimal config in paper), Then...