Low-Resolution Face Recognition In Resource-Constrained Environments

TL;DR

This paper introduces a low-resolution face recognition model tailored for resource-limited environments, leveraging successive subspace learning for explainability, low training complexity, and adaptability with small datasets.

Contribution

It proposes a novel non-parametric SSL-based face recognition approach suitable for resource-constrained settings, emphasizing explainability and low training complexity.

Findings

Effective on LFW and CMU Multi-PIE datasets.

Low training complexity due to one-pass feedforward learning.

Model flexibility with trade-offs between size and performance.

Abstract

A non-parametric low-resolution face recognition model for resource-constrained environments with limited networking and computing is proposed in this work. Such environments often demand a small model capable of being effectively trained on a small number of labeled data samples, with low training complexity, and low-resolution input images. To address these challenges, we adopt an emerging explainable machine learning methodology called successive subspace learning (SSL).SSL offers an explainable non-parametric model that flexibly trades the model size for verification performance. Its training complexity is significantly lower since its model is trained in a one-pass feedforward manner without backpropagation. Furthermore, active learning can be conveniently incorporated to reduce the labeling cost. The effectiveness of the proposed model is demonstrated by experiments on the LFW and the CMU Multi-PIE datasets.