Question about results on ScanNet. Why result of paper v2 is significantly higher than that of paper v1?

[charlesCXK]

Hi, I have a question about the results on ScanNet dataset. I find that [email protected] is reported to be 46.75% in the first version of your paper, while [email protected] is boosted to be 58.6% in the version 2. Could you tell me how do you gain such an amazing increase? Thank you !

[charlesCXK]

We reproduced VoteNet according to the setting in the paper versio-1, and got a reasonable result on SUNRGBD. However, we only got [email protected] on ScanNet, which is reasonable when compared with paper version-1, but is far lower than the result in paper version-2. Thus we create this issue.

[charlesq34]

Hi @charlesCXK

The major change is the learning rate scheduling. Originally we have exponential decay of the learning rate for paper version-1. Later we updated it to step-wise learning rate decay with the same intervals as that for SUN RGB-D training (80,120,160 epochs). The delayed decay of the learning contributed to the performance boost.

[charlesCXK]

Thanks! We will check it. @charlesq34