search

lxtGH / CAE

This is a PyTorch implementation of “Context AutoEncoder for Self-Supervised Representation Learning"
193 stars 22 forks source link

imagenet result of CAE-large model with 800 epochs #17

Closed russellllaputa closed 1 year ago

russellllaputa commented 1 year ago

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 1 year ago

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