xiao7199

Results 6 comments of xiao7199

Question on Table 6

Also, cloud you please provide the config to reproduce the experiment in Table6? Thanks!

the pre-training loss

Hi, If I understand correctly, this regreission loss only includes the pushing force with aligning spatial corresponding pixel. So where is the repulsing force as in Eqn2?

Parallel loading with torch.utils.data.DataLoader

Are you using cpu(0) with num_of_workers > 1?

Parallel loading with torch.utils.data.DataLoader

Could you please share your code for this part? I've been facing a similar issue recently. Thanks!

roi-pooling for RCNN

Hi @marcopede, have you find out the reason yet? Is there any chance that the instability is something to do with in appropriate training procedure, i.e. the alternative training ?

The DINO baseline is higher than STEGO.

Hi Alex, Thanks for sharing the draft and the results. I think the results from Table 2 are consistent with what I've found. Best, Xiao.