Have you tried Hungarian matching instead of optimal transport assignment?

[dk-liang]

Have you tried Hungarian matching instead of optimal transport assignment?

[ShoufaChen]

Hi,

Thanks for your interest.

We tried Hungarian matching in our pilot experiments and found that assigning multiple predictions to ground truth is better for DiffusionDet.

[dk-liang]

Thanks for your reply. Could you tell me the performance gap between OT and Hungarian?

[ShoufaChen]

Hi, @dk-liang ,

Apologies for the delayed response. At the initial stage of the project, we conducted a comparison between OT and Hungarian, but we don't have any quantifiable data at this time. We plan to perform additional experiments to gather these metrics.

Please stay tuned for updates.

[lpdone]

May I ask the difference between the results of the two operations, is there any result now? Thanks