Skip to content

Why use the features of last 4 layers?  #81

@Kal-Elll

Description

@Kal-Elll

We note that you use the features of last 4 layers from the encoder instead of intermediate layers (e.g. [5, 12, 18, 24] for vitl) as in some other works such as DINOv2. What's the reason for that and is there any remarkable difference between these two strategy?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions