Displaying 1 to 4 from 4 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.

batch-feature-erasing-network - Official source code of Batch Feature Erasing for Person Re-identification and Beyond

  •    Python

Update CUHK03 results. Traning scripts are released. The best Markt1501 result is 95.3%! Please look at the training section of README.md.

S-WMD - Code for Supervised Word Mover's Distance (SWMD)

  •    Matlab

A demo code in Matlab for S-WMD [Supervised Word Mover's Distance, NIPS 2016] [Oral presentation video recording by Matt Kusner]. The only difference with the above datasets is that because there are pre-defined train-test splits, there are already variables BOW_xtr, BOW_xte, xtr, xte, ytr, yte.