A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
In Defense of the Triplet Loss Again: Learning Robust Person Re-Identification with Fast Approximated Triplet Loss and Label Distillation
[article]
2019
arXiv
pre-print
The comparative losses (typically, triplet loss) are appealing choices for learning person re-identification (ReID) features. However, the triplet loss is computationally much more expensive than the (practically more popular) classification loss, limiting their wider usage in massive datasets. Moreover, the abundance of label noise and outliers in ReID datasets may also put the margin-based loss in jeopardy. This work addresses the above two shortcomings of triplet loss, extending its
arXiv:1912.07863v2
fatcat:z3z3wipixnhxvncthhn3s4ytxq