NPT-Loss: A Metric Loss with Implicit Mining for Face Recognition
arXiv:2103.03503
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.
References in corpus (6)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Learning Face Representation from Scratch
- Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments
- SoftTriple Loss: Deep Metric Learning Without Triplet Sampling
- Crystal Loss and Quality Pooling for Unconstrained Face Verification and Recognition
- FAN: Feature Adaptation Network for Surveillance Face Recognition and Normalization