In this work, we investigate several methods and strategies to learn deep embeddings for face recognition, using joint sample- and set-based optimization. We explain our framework that expands traditional learning with set-based supervision together with the strategies used to maintain set characteristics. We, then, briefly review the related set-based loss functions, and subsequently propose a novel Max-Margin Loss which maximizes maximum possible inter-class margin with assistance of Support Vector Machines (SVMs). It implicitly pushes all the samples towards correct side of the margin with a vector perpendicular to the hyperplane and a strength exponentially growing towards to negative side of the hyperplane. We show that the introduced loss outperform the previous sample-based and set-based ones in terms verification of faces on two commonly used benchmarks.
@article{arxiv.1708.00277,
title = {Learning Deep Convolutional Embeddings for Face Representation Using Joint Sample- and Set-based Supervision},
author = {Baris Gecer and Vassileios Balntas and Tae-Kyun Kim},
journal= {arXiv preprint arXiv:1708.00277},
year = {2020}
}