Rui Tian

Hi @dedeswim. Thanks for reaching out. The models we use are identical with architectures in timm and our checkpoints can be loaded directly onto `deit_{small,base}_patch16_224`. So it would be feasible...

Hi, sorry for late reply, I uploaded according results for [ImageNet-C](https://drive.google.com/file/d/11uUpXzS9HLIszIrR5cwIfl9JcqA1Y7-q/view?usp=sharing) and [ImageNet-3DCC](https://drive.google.com/file/d/1BI6FCR1IXg6tw0o4Es2M9BN3DRdMBk76/view?usp=sharing).

Hi @dedeswim, sorry for late reply. Besides, thanks for your great efforts. If necessary, we further provide results on full datasets of [IN-3DCC](https://drive.google.com/file/d/15l0pefxamimMiYYsiHkTm3BVltQwKEVS/view?usp=share_link) and [IN-C](https://drive.google.com/file/d/1XpHIva-F_Ou9G5lsNg2gtkq8Z0yclAlJ/view?usp=share_link) (which also includes mCE) since...

Hi @dedeswim, Thanks for your concerns! Since results on full datasets cannot be implemented with single gpu, we do change the evaluation code. We base full-results evaluation on IN-3DCC on...

Hi @dedeswim, Thanks for your careful checks and kind suggestion! After going over the evaluation code, I figured out that the misalignment is caused by failing to conduct normalization when...

Hi @dedeswim, Sorry for the late update. I have uploaded the corrected results on [IN-C](https://drive.google.com/file/d/1beTbot_lWAZtLdFsro-SNOoHRxaOJqOP/view?usp=sharing) and [IN-3DCC](https://drive.google.com/file/d/1BI6FCR1IXg6tw0o4Es2M9BN3DRdMBk76/view?usp=sharing ) for both 5000 samples and full datasets. Particularly, I noticed that there...

Hi, @dedeswim. Sorry to bother you about the merge. I have already updated the results as mentioned above. Feel free to inform me if there exists any additional concerns. Thanks!

Hi @max-andr, The evaluation results are sound since we also saw a slight drop in performance with an upgraded Pillow version in previous experiments. Thanks for your great efforts! Best,...