About Voting Strategy

[a18700]

Hello, i'm interested in your paper, curvenet.

Where can I access to the voting strategy that you used in your M40 experiments?

Thank you.

[tiangexiang]

Hi, thanks for your interest! As mentioned in README.md, we used the exact voting scripts provided in RSCNN. Simply update the scripts with our dataloader/model and you are good to go:) Since the voting process is highly sensitive to randomness, same to RSCNN, we repeated the voting 300 times, and reported the best score.