Zhengkai Jiang

icon indicating a website link https://jiangzhengkai.github.io/

icon company Tencent icon location Shanghai icon location Computer Vision and Deep Learning

Results 11 issues of Zhengkai Jiang

About Batch Normalization Statistics When using Domain Adaptation Setting

1 comment

Hi, thanks for your wonderful work. From the paper, the batch normalization statistics updates for combined source and target images, and keep fixed when computing source images for the second...

pretrained model for Swin-v2?

1 comment

Thanks for your great repo. I would like to ask when the swin-v2 pre-trained model will be released?

How about the performance when replacing Deformable DETR to the original DETR?

Hi, thanks for your good work. I want to know the performance only using the original DETR instead of the improved Deformable DETR for a fair comparison with IFC paper.

plz add some annotation for the tf code

traning is much slower than reported in the paper!

3 comment

pretrained model?

Any Python evaluation code available?

1 comment

When do you release the code?

eqlv2 for focal loss

2 comment

I want to know how to use eqlv2 for dense object detection which uses focal loss for classification? Any ideas?

About FLOPS and Parameters of Mask R-CNN

How do you calculate the flops and parameters for Mask R-CNN model? I use analyze_model provided by detectron2, which is not consistent with your results. Would you mind share the...