Skip to content

about the loss #6

Description

@licheer-jian

First of all,thank you for your work,it helps a lot,but I have a question:
In the article,you mentioned "Integrating GDIP with Yolo in this fashion ensures that our architecture doesn’t require any additional loss formulation and uses Yolo’s standard object detection loss [37] (referred to as Lobj) to train the network for object detection end-to-end."

I do not understand why additional loss is not required,looking forward to your reply,thank you!

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Fields

    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions