What's the defferences of results on ImageNet-C between Table 11 and Table 8?

[jiequancui]

Hi,

Thanks for your excellent work.

What are the differences in results on ImageNet-C between Table 11 and Table 8?

For example, with FAN-L-Hybrid, It is 68.3 in Table 8 and 43.0 in Table 11.

[zhoudaquan]

Hi,

Thanks for your excellent work.

What are the differences in results on ImageNet-C between Table 11 and Table 8?

For example, with FAN-L-Hybrid, It is 68.3 in Table 8 and 43.0 in Table 11.

Hi,

Thanks for the interest. 68.3 is referring to the average accuracy across different categories while in Table 11, we use mCE to align the comparison with other methods.