PSNet: Parametric Sigmoid Norm Based CNN for Face Recognition

TL;DR

This paper introduces PSNet, a CNN model with a Parametric Sigmoid Norm layer that improves face recognition by better handling hard examples, demonstrated on LFW and YTF datasets.

Contribution

The paper proposes a novel PSN layer integrated into CNNs to enhance learning from hard examples in face recognition tasks.

Findings

PSN layer improves gradient flow for hard examples

Enhanced face recognition accuracy on LFW and YTF datasets

Compatibility of PSN layer with various loss functions

Abstract

The Convolutional Neural Networks (CNN) have become very popular recently due to its outstanding performance in various computer vision applications. It is also used over widely studied face recognition problem. However, the existing layers of CNN are unable to cope with the problem of hard examples which generally produce lower class scores. Thus, the existing methods become biased towards the easy examples. In this paper, we resolve this problem by incorporating a Parametric Sigmoid Norm (PSN) layer just before the final fully-connected layer. We propose a PSNet CNN model by using the PSN layer. The PSN layer facilitates high gradient flow for harder examples as compared to easy examples. Thus, it forces the network to learn the visual characteristics of hard examples. We conduct the face recognition experiments to test the performance of PSN layer. The suitability of the PSN layer with different loss functions is also experimented. The widely used Labeled Faces in the Wild (LFW) and YouTube Faces (YTF) datasets are used in the experiments. The experimental results confirm the relevance of the proposed PSN layer.