Skip connection indexing in Swin3DTransformerBackbone.forward: mismatch with paper's backbone figure?

Hi, I am currently working on latent space data of Aurora for interpretability research at LMU. I found that spatial plots of latent states of encoding stage 1 strongly resemble those of decoding stage 3, which I didn't expect.

I checked the forward method of Swin3DTransformerBackbone in swin3d.py (https://github.com/microsoft/aurora/blob/639b4e8a8c1d96b12949b41547bce66006218c91/aurora/model/swin3d.py#L1026-L1055) and to me it seems the skip connections are different than shown in the backbone figure of the paper. I am running version v1.8.0, in which this decoder loop logic is the same as shown here.

Tracing the decoder loop (for i, layer in enumerate(self.decoder_layers), index = self.num_decoder_layers - i - 1):

• i=0 (index=2): No skip connection is applied at all. The 0 < i condition in the additive-skip check excludes this case, and i == num_decoder_layers - 1 doesn't match either.
• i=1 (index=1): skips[0] (output of encoding stage 1) is added additively to the input of decoding stage 3.
• i=2 (index=0): skips[0] is concatenated again to the output of decoding stage 3.

So skips[0] is used twice: once additively before decoding stage 3, and once via concatenation after decoding stage 3. Meanwhile skips[1] (encoding stage 2's output) is not used at all.

Is this intentional, or should skips[1] be used somewhere in the decoder as well? I might be misreading the loop, so let me know if I'm missing something.

Start in swin3d.py at the Swin3DTransformerBackbone.forward method around lines 1026-1055, then compare the decoder loop with the backbone figure in the paper. Trace each decoder iteration and the uses of skips[0] and skips[1]. Done means establishing the intended skip-connection mapping and clearly documenting whether the implementation or the figure needs correction.