Displaying 1 to 3 from 3 results

AMSoftmax - A simple yet effective loss function for face verification.

  •    Matlab

The paper is available as a technical report at arXiv. In this work, we design a new loss function which merges the merits of both NormFace and SphereFace. It is much easier to understand and train, and outperforms the previous state-of-the-art loss function (SphereFace) by 2-5% on MegaFace.

catboost-viewer - Standalone application for plotting charts with different training statistics in a browser

  •    Javascript

You need Node.js and NPM installed. You can do this from download or by package manager. After that you will get globally installed catboost-viewer executable.

LovaszSoftmax - Code for the Lovász-Softmax loss (CVPR 2018)

  •    Jupyter

ESAT-PSI, KU Leuven, Belgium. Published in CVPR 2018. See project page, arxiv paper, paper on CVF open access.