vitae-transformer/vitae-vsa

The official repo for [ECCV'22] "VSA: Learning Varied-Size Window Attention in Vision Transformers"

vitae-vsa's Issues

img_size in VSA attention

Hello, i would like to ask about the setting of img_size=(1,1) in line 36 vsa.py. Which size does it mean? thanks a lot.

Can you release the pretrained model for ViTAEv2*-VSA-B?

@Qiming-Zhang1 @RogerZhangzz

pre-trained model of Swin + VSA

hello, i am now doing a work about semantic segmentation and i would like to use swin with vsa model as the feature extractor backbone. I would like to ask, about when will you maybe upload the pre-trained model? Without pretrained model the results are really with low accuracy now... Thank you so much.

Is it possible the positional encoding rather than VSA works？

In your code file ViTAE-VSA\Image-Classification\vitaev2_vsa\NormalCell.py L130:
self.pos = nn.Conv2d(dim, dim, window_size//2*2+1, 1, window_size//2, groups=dim, bias=True)
your window_sizeis 7，so the self.pos convolution kernel is 7 too, in most Positional Encoding extractor it is so large.

So is it possible that the positional encoding rather than VSA is working ？

How to use the weights weight file provided？

I would like to ask how to use the provided weights pre-training file, .tar type zipped file extracted without a .pth file, but a folder

Swin+VSA

语义分割和 Swin+VSA 什么时候发布呀

When will the code be released?

After 5 months，When will the code be released?

where is the model which vsa is added to swin transformer?

Hello!
I hope to have the model that just adding vsa to swin transformer like said in the paper.
Can you release the code?
Thank you very much.