The 5-shot evaluation is problematic

[happycoding1996]

Hi, thanks for your work.

I have reproduced the 1-shot results that are close to the ones in your paper.

However, when I directly test the model trained with 1-shot in the 5-shot evaluation setting, the result is far from yours.

For example, on fold 0, the 1-shot result is 59.2 and 5-shot I only got 43.73.

Could you help fix this issue?

Thankyou.

[Reagan1311]

Sorry for the late reply. The 5-shot results are tested in the model trained with 5-shots.

You may refer to this paper, it proves directly testing the 1-shot model in prototypical networks will lead to a saturation in 5-shot performance.

[happycoding1996]

@Reagan1311 Thank you for your reply!