Skip to content

One issue about the loss function #2

Open

Description

@abcxubu

Thanks for sharing the code of the wonderful work. I have a problem with the loss function. In section 2.2, it introduces the loss function of knowledge distillation, which is used to obtain the high entropy. In section 2.3, it introduces the loss function of uncertainty minimization, which is used to obtain the low entropy. Will there be a conflict between these two loss functions? I hope to receive your reply as soon as possible.

Activity

  1. lanfz2000 commented on Aug 24, 2023

    @lanfz2000
    Collaborator

    The experimental results demonstrate that these two loss functions are not contradictory. Regarding the issue you mentioned, I believe that the loss function based on Knowledge Distillation (KD) does not increase entropy.

  2. abcxubu commented on Aug 25, 2023

    @abcxubu
    Author

    In section 2.2, you said "Note that T = 1 corresponds to a standard
    Softmax function, and a larger T value leads to a softer probability distribution
    with higher entropy. ". In the experiment, you set T=10. Could you explain how the knowledge distillation works in principle? (rather than just answering this question from the perspective of experimental results) Thanks.

  3. lanfz2000 commented on Aug 25, 2023

    @lanfz2000
    Collaborator
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