Skip to content

Trained model performance without TTT #7

Description

@HaochenZ11

Hi, thank you for this work.

Was there an ablation done to measure the performance of the trained model (pretrained on spatial datasets) but without any test-time updates?

I tried this with the released nano checkpoint and performance was around the same as with TTT, which seems surprising as it suggests that the gradient steps at test-time do not contribute much to the performance.

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

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