With BiFPN about actionformer_release HOT 4 CLOSED

Mix maxpool1D and Conv1D as downsampling operator, following CSP convolution.
Although the accuracy of actionformer used in my dataset has been improved a lot(thanks you again for the great work), it is not enough, so I want to add some other tricks to improve the accuracy.

from actionformer_release.

Hi, thank you for your interest in our ActionFormer.

As you can see, we have supported the traditional FPN structure in the neck part. However, we find that 1D FPN does not boost the performance. Some other papers also have this observations. So simply modifing FPN structures may not improve the accuracy. If you want to improve the accuracy, a good choice is to decrease the temproal stride (use more dense features) or switching the backbone, using the very recent Transformer backbone should help here.

from actionformer_release.

@tzzcl Thanks for your valuable suggestion.

from actionformer_release.

Closed due to inactivity.

from actionformer_release.