English

NPT-Loss: A Metric Loss with Implicit Mining for Face Recognition

Computer Vision and Pattern Recognition 2021-03-08 v1 Machine Learning

Abstract

Face recognition (FR) using deep convolutional neural networks (DCNNs) has seen remarkable success in recent years. One key ingredient of DCNN-based FR is the appropriate design of a loss function that ensures discrimination between various identities. The state-of-the-art (SOTA) solutions utilise normalised Softmax loss with additive and/or multiplicative margins. Despite being popular, these Softmax+margin based losses are not theoretically motivated and the effectiveness of a margin is justified only intuitively. In this work, we utilise an alternative framework that offers a more direct mechanism of achieving discrimination among the features of various identities. We propose a novel loss that is equivalent to a triplet loss with proxies and an implicit mechanism of hard-negative mining. We give theoretical justification that minimising the proposed loss ensures a minimum separability between all identities. The proposed loss is simple to implement and does not require heavy hyper-parameter tuning as in the SOTA solutions. We give empirical evidence that despite its simplicity, the proposed loss consistently achieves SOTA performance in various benchmarks for both high-resolution and low-resolution FR tasks.

Keywords

Cite

@article{arxiv.2103.03503,
  title  = {NPT-Loss: A Metric Loss with Implicit Mining for Face Recognition},
  author = {Syed Safwan Khalid and Muhammad Awais and Chi-Ho Chan and Zhenhua Feng and Ammarah Farooq and Ali Akbari and Josef Kittler},
  journal= {arXiv preprint arXiv:2103.03503},
  year   = {2021}
}
R2 v1 2026-06-23T23:47:23.399Z