Question about Cross-view Hybrid attention

[jianingwangind]

Thanks for sharing the great work.

Regarding to Cross-view Hybrid attention, is it only apllied for the HW top plane?

TPVFormer/tpvformer04/modules/tpvformer_layer.py

Line 172 in 2073589

query[0],

The query is itself, key and value are both none while later in cross-view hybrid attention the value is set to be the concatenation of queries

TPVFormer/tpvformer04/modules/cross_view_hybrid_attention.py

Line 163 in 2073589

value = torch.cat([query, query], 0)

[yuhanglu2000]

I have the same question, it looks like there is no interaction between the features of the three planes.

[huang-yh]

Thanks for your interest in our work.
Your understanding of the code is correct. That is, in TPVFormer04, cross-view hybrid attention is enabled only in the HW plane, thus degrading to self-attention.

[jianingwangind]

@huang-yh Thanks for your reply. May i further ask the idea behind this? Similar performance when disabling the attention in the other two planes?