rafaelvareto/maximal-entropy-loss rafaelvareto/maximal-entropy-loss

  • Stars
    star
    2
  • Language
    Jupyter Notebook
  • License
    GNU General Publi...
  • Created about 1 year ago
  • Updated 11 months ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
rafaelvareto/maximal-entropy-loss
github

rafaelvareto

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

OpenLoss: This repository discloses cost functions designed for open-set classification tasks, namely, Entropic Open-set, ObjectoSphere and Maximal-Entropy Loss.

More Repositories

1

HPLS-HFCN-openset

Paper: Towards Open-Set Face Recognition using Hashing Functions (IJCB'17)
Python
13
star
2

Spoofing-CIARP19

Paper: Face Spoofing Detection on Low-Power Devices using Embeddings with Spatial and Frequency-based Descriptors (CIARP'19)
Python
4
star
3

HPLS-verification

Paper: Face Verification based on Relational Disparity Features and Partial Least Squares Models (SIBGRAPI'17)
Python
1
star
4

distance-transform-loss

This repository discloses a new cost function entitled Distance Transform Loss (DTL) that punishes deep networks when class boundaries are misclassified in exchange for more accurate contour delineations, an important aspect in the geological field.
1
star