BGNN performance without BLS

[hesedjds]

Thank you for your great job!
We want to check the effect of BLS, so we tried to reproduce Table 3 in the paper (The ablation for the resampling strategy).

We used the same config file with the demo script (e2e_relBGNN_vg.yaml), but we just changed it as below:
MODEL.ROI_RELATION_HEAD.DATA_RESAMPLING None
MODEL.ROI_RELATION_HEAD.DATA_RESAMPLING_METHOD None

However, we just got less performance than the paper:

	mR@20	mR@50	mR@100	R@20	R@50	R@100
Our	4.9	7.09	8.85	23.76	31.38	38.06
Paper	-	-	9.7	-	-	36.1

Can you share your config file for Table 3?

[Scarecrow0]

Hi,
Thanks for being interested in our work.
It seems that your modification is correct.
This ablation result is conducted on the codebase before refactoring. I'm checking this ablation on the current code base. I will send you the configuration or trained parameters.