lxtGH/CAE

imagenet result of CAE-large model with 800 epochs

russellllaputa opened this issue · 1 comments

russellllaputa commented

Dear authors,

Thank you for your excellent work.
Could you also provide the accuracy of ViT-Large in an 800-epoch pre-training scheme?

Thank you for your grateful help

Best wishes,

charlesCXK commented

Linear probing: 76.3
Atentive probing: 80.0
ImageNet finetuning: 86.0
Semantic Segmentation: 54.4