Closed makecent closed 2 years ago
I guess a major performance drop may come from the duplicate action part, i.e., Diving and Cliff Diving as in #10. When we disable the score fusion, we can provide predictions for both Diving and Cliff Diving. But when we enable the score fusion, one category may be supressed.
@tzzcl According to #10, if we disable the score fusion, actionformer can not predict Cliff_Diving
at all as it never saw an training sample from this category.
I still don't get the reason why fusion with external score will get worse result. And if it's true, why even bothering ourselves with the external score?
When I refer to #10, I mean that there exists multiple labels for the same action. ActionFormer cannot handle this situation previously, but we fix that issue in a commit. Thus, when we disable the score fusion, ActionFormer can predict multiple action labels with same interval. When we enable the score fusion, we may can not do this part.
I see. It's great to get rid of the external scores.
Thanks.
My understanding is that enabling score fusion will use the external classification score, which should lead to better results. However, when I disabling the score fusion, i.e.,:
The eval result is:
While when enabling the score fusion, i.e.,:
I got a worse result:
BTW, I did NOT retrain the model after revising the yaml because I think this should only do with the testing.