A Performance Comparison of Loss Functions for Deep Face Recognition

Abstract

Face recognition is one of the most widely publicized feature in the devices today and hence represents an important problem that should be studied with the utmost priority. As per the recent trends, the Convolutional Neural Network (CNN) based approaches are highly successful in many tasks of Computer Vision including face recognition. The loss function is used on the top of CNN to judge the goodness of any network. In this paper, we present a performance comparison of different loss functions such as Cross-Entropy, Angular Softmax, Additive-Margin Softmax, ArcFace and Marginal Loss for face recognition. The experiments are conducted with two CNN architectures namely, ResNet and MobileNet. Two widely used face datasets namely, CASIA-Webface and MS-Celeb-1M are used for the training and benchmark Labeled Faces in the Wild (LFW) face dataset is used for the testing.

arXiv commentAccepted in NCVPRIPG 2019 Conference

References in corpus (16)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• An overview of gradient descent optimization algorithms
• MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
• Deep Learning Face Representation by Joint Identification-Verification
• Learning Face Representation from Scratch
• CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
• Rethinking the Inception Architecture for Computer Vision
• Highway Networks
• Large-Margin Softmax Loss for Convolutional Neural Networks
• Aggregated Residual Transformations for Deep Neural Networks
• Xception: Deep Learning with Depthwise Separable Convolutions
• Learning Deep Features via Congenerous Cosine Loss for Person Recognition
• Range Loss for Deep Face Recognition with Long-tail
• Minimum Margin Loss for Deep Face Recognition

Cited by in corpus (3)

• Neural Architecture Search for Deep Face Recognition
• Evaluation of Dataflow through layers of Deep Neural Networks in Classification and Regression Problems
• Frequency Disentangled Residual Network