Some questions about Soft-Teacher method about softteacher

[MendelXu]

Yes, the inputs to both models are transformed with different augmentations. To calculate the loss between the student and teacher model, we have to map the coordinates to the same space. We use the transform_matrix to record the augmentation information. And then we are able to align inputs auged with different augmentations with the matrix.

[songbae]

Yes, the inputs to both models are transformed with different augmentations. To calculate the loss between the student and teacher model, we have to map the coordinates to the same space. We use the transform_matrix to record the augmentation information. And then we are able to align inputs auged with different augmentations with the matrix.

thanks! clearly understood

[cnmckee]

I have another question- can't seem to find it in the paper. At inference time, is the teacher model or student model used for inference? Thanks.

[MendelXu]

@cnmckee In our paper and provided code, we use the student model for inference. However, in some cases, the teacher performs somewhat better than the student. So just for advice, you can try them both to see which is better.

[cnmckee]

@cnmckee In our paper and provided code, we use the student model for inference. However, in some cases, the teacher performs somewhat better than the student. So just for advice, you can try them both to see which is better.

Makes sense- thanks for the speedy reply!