Closed mrluin closed 2 years ago
Thanks for your question. It means K/V should be sampled for 9 times.
Thanks for your quick reply. Sampling 9 times on K/V and performing 9 times attention for each Q, and then aggregation, right? Does it comsumes too much GPU memory?
The attention is used for aggregation. We wrote it with cuda, so the memory is controllable.
Sorry for another question under the closed issue.
In ablation study, I notice that you give comparisons on different alignment methods, the improvement of GDA* is about 0.07db compared with DCN. And commonly, flow-guided deformable convolution is more stable and with better performance than DCN, so how about the performance if conducting attention on K/V which are aligned by flow-guided deformable convolution?
Thanks in advance.
I haven't trained that yet, but it looks too complex (not elegant) if we stack them together.
Hello,
Thanks for your great work!
I have a question about
candidates
of GDA. I think candidates=9 means one position in Q should calculate correlation with 9 positions in K and V like what illustrated in Figure 3. Does it means the dimension of K/V should expand 9 times?Looking forward to your reply, thanks!