ruizhaoz

Hello, I was trying to replicate the results reported in the paper but failed. Could you share the parameter setting when you run ResNet12 as backbone and ProtoNet head as...

Hi, are there any way to directly evaluate pretrained model?

Hi, this is an interesting paper. I wonder if you have tested the effectiveness use STEGO on object detection for downstream task. Since segmentation seems to be a more difficult...

ViT Performance

1

Hello, I tried out the code, and it is very neat and it works fine. One question I noticed is the ViT-b performance (Table 9) is much worse than the...

Why can't use SAM encoder to get extracted feature?

2

Have you try directly use SAM encoder to extract feature instead use other pretrained model?