FusiformNet: Extracting Discriminative Facial Features on Different Levels

TL;DR

FusiformNet is a novel facial feature extraction framework that captures both general and local discriminative features, achieving state-of-the-art accuracy on challenging benchmarks without relying on data augmentation or specialized loss functions.

Contribution

The paper introduces FusiformNet, a new framework that leverages the nature of facial differences to improve recognition accuracy without additional data or complex training strategies.

Findings

Achieved 96.67% accuracy on LFW without external data.

Performs comparably to state-of-the-art methods with pre-training.

Effective in extracting both global and local facial features.

Abstract

Over the last several years, research on facial recognition based on Deep Neural Network has evolved with approaches like task-specific loss functions, image normalization and augmentation, network architectures, etc. However, there have been few approaches with attention to how human faces differ from person to person. Premising that inter-personal differences are found both generally and locally on the human face, I propose FusiformNet, a novel framework for feature extraction that leverages the nature of discriminative facial features. Tested on Image-Unrestricted setting of Labeled Faces in the Wild benchmark, this method achieved a state-of-the-art accuracy of 96.67% without labeled outside data, image augmentation, normalization, or special loss functions. Likewise, the method also performed on a par with previous state-of-the-arts when pre-trained on CASIA-WebFace dataset. Considering its ability to extract both general and local facial features, the utility of FusiformNet may not be limited to facial recognition but also extend to other DNN-based tasks.