Skip to content

kNN classification on pretrained checkpoints #1

Description

@bourcierj

Hi,

I am trying to use the provided ViT-Large checkpoint of Cross-Scale-MAE to perform inference and kNN classification on features. When I test it on the RESISC45 dataset, I get relatively low accuracy (0.6211). I expect it to be much higher given your results in the paper.

Could you provide the expected performance on RESISC45 at 100% scale ratio, for comparison ? This would help for debugging and give me a target to reproduce.

Some details: I am using the RESISC45 train/test splits from torchgeo, image size = 256 (which should correspond to 100% scale ratio I believe), k = 5.

Thank you.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions