• Home
  • Search
  • Range Loss for Deep Face Recognition with Long-Tailed Training Data
  • Cite Icon525
  • https://doi.org/10.1109/iccv.2017.578Copy DOI Icon

Range Loss for Deep Face Recognition with Long-Tailed Training Data

  • Oct 1, 2017
  • Xiao Zhang +4 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Deep convolutional neural networks have achieved significant improvements on face recognition task due to their ability to learn highly discriminative features from tremendous amounts of face images. Many large scale face datasets exhibit long-tail distribution where a small number of entities (persons) have large number of face images while a large number of persons only have very few face samples (long tail). Most of the existing works alleviate this problem by simply cutting the tailed data and only keep identities with enough number of examples. Unlike these work, this paper investigated how long-tailed data impact the training of face CNNs and develop a novel loss function, called range loss, to effectively utilize the tailed data in training process. More specifically, range loss is designed to reduce overall intrapersonal variations while enlarge interpersonal differences simultaneously. Extensive experiments on two face recognition benchmarks, Labeled Faces in the Wild (LFW) [11] and YouTube Faces (YTF) [33], demonstrate the effectiveness of the proposed range loss in overcoming the long tail effect, and show the good generalization ability of the proposed methods.

Similar Papers
  • Book Chapter
  • Citations4544

A Discriminative Feature Learning Approach for Deep Face Recognition

  • Jan 01, 2016
  • Yandong Wen +3
  • Conference Article
  • Citations41

Face and Gender Recognition System Based on Convolutional Neural networks

  • Aug 01, 2019
  • Yuxiang Zhou +3
  • PDF
  • Research Article
  • Citations184

Deep Convolutional Neural Network-Based Approaches for Face Recognition

  • Oct 17, 2019
  • Applied Sciences
  • Soad Almabdy +1
  • Research Article
  • Citations17

Additive Parameter for Deep Face Recognition

  • Dec 12, 2019
  • Communications in Mathematics and Statistics
  • Jamshaid Ul Rahman +2
  • Conference Article
  • Citations3134

CosFace: Large Margin Cosine Loss for Deep Face Recognition

  • Jun 01, 2018
  • Hao Wang +7
  • Book Chapter
  • Citations13

Hard-Mining Loss Based Convolutional Neural Network for Face Recognition

  • Jan 01, 2021
  • Yash Srivastava +2
  • Conference Article
  • Citations55

Simple Triplet Loss Based on Intra/Inter-Class Metric Learning for Face Verification

  • Oct 01, 2017
  • Zuheng Ming +4
  • Conference Article
  • Citations13

PSNet: Parametric Sigmoid Norm Based CNN for Face Recognition

  • Dec 01, 2019
  • Yash Srivastava +2
  • Conference Article
  • Citations31

A Cross Benchmark Assessment of a Deep Convolutional Neural Network for Face Recognition

  • May 01, 2017
  • P Jonathon Phillips
  • Conference Article
  • Citations279

Marginal Loss for Deep Face Recognition

  • Jul 01, 2017
  • Jiankang Deng +2
  • Conference Article
  • Citations7

Face recognition by landmark pooling-based CNN with concentrate loss

  • Sep 01, 2017
  • Rui Huang +3
  • Book Chapter
  • Citations2

DynFace: A Multi-label, Dynamic-Margin-Softmax Face Recognition Model

  • Apr 24, 2019
  • Marius Cordea +3
  • Book Chapter
  • Citations6

Effect of Laplacian Smoothing Stochastic Gradient Descent with Angular Margin Softmax Loss on Face Recognition

  • Jan 01, 2020
  • Mansoor Iqbal +3
  • Research Article
  • Citations57

A deep learning approach for face recognition based on angularly discriminative features

  • Oct 03, 2019
  • Pattern Recognition Letters
  • Mansoor Iqbal +4
  • Conference Article
  • Citations2

Performance Analysis of Deep Learning based Face Recognition Model for Video Surveillance

  • Dec 16, 2022
  • Shahina Anwarul +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.