Swin-MAE

Swin-MAE copied to clipboard

Why not use SwinV2 as Encoder?

1

SwinV2 which is an enhancing version based on SwinV1 has many merits beyond its predecesor, such as more stable training performance, using log pos_emb to support larger resolution, So I...

ttjjmm

Hi thanks for the contribution, I would like to ask, how can I get the embeddings in a dimension of 1x dim?

dnnxl

Question about Fig.2 in paper

2

Hi there, thanks for your great work! I got a question when I read the paper. I am curious about the middle (reconstruction) image in Fig.2. It looks like the...

Spritea