• Home
  • Search
  • RVFace: Reliable Vector Guided Softmax Loss for Face Recognition.
  • Cite Icon18
  • https://doi.org/10.1109/tip.2022.3154293Copy DOI Icon

RVFace: Reliable Vector Guided Softmax Loss for Face Recognition.

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Face recognition has witnessed significant progress with the advances of deep convolutional neural networks (CNNs), and the central task of which is how to improve the feature discrimination. To this end, several margin-based (e.g., angular, additive and additive angular margins) softmax loss functions have been proposed to increase the feature margin between different classes. However, despite great achievements have been made, they mainly suffer from four issues: 1) They are based on the assumption of well-cleaned training sets, without considering the consequence of noisy labels inherently existing in most of face recognition datasets; 2) They ignore the importance of informative (e.g., semi-hard) features mining for discriminative learning; 3) They encourage the feature margin only from the perspective of ground truth class, without realizing the discriminability from other non-ground truth classes; and 4) They set the feature margin between different classes to be same and fixed, which may not adapt the situation of unbalanced data in different classes very well. To cope with these issues, this paper develops a novel loss function, which explicitly estimates the noisy labels to drop them and adaptively emphasizes the semi-hard feature vectors from the remaining reliable ones to guide the discriminative feature learning. Thus we can address all the above issues and achieve more discriminative features for face recognition. To the best of our knowledge, this is the first attempt to inherit the advantages of feature-based noisy labels detection, feature mining and feature margin into a unified loss function. Extensive experimental results on a variety of face recognition benchmarks have demonstrated the effectiveness of our method over state-of-the-art alternatives. Our source code is available at http://www.cbsr.ia.ac.cn/users/xiaobowang/.

Similar Papers
  • Research Article
  • Citations194

Mis-Classified Vector Guided Softmax Loss for Face Recognition

  • Apr 03, 2020
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Xiaobo Wang +5
  • Book Chapter
  • Citations4544

A Discriminative Feature Learning Approach for Deep Face Recognition

  • Jan 01, 2016
  • Yandong Wen +3
  • PDF
  • Research Article
  • Citations13

Double Additive Margin Softmax Loss for Face Recognition

  • Dec 19, 2019
  • Applied Sciences
  • Shengwei Zhou +3
  • Research Article
  • Citations16

Aerial scene classification via an ensemble extreme learning machine classifier based on discriminative hybrid convolutional neural networks features

  • Oct 22, 2018
  • International Journal of Remote Sensing
  • Lihua Ye +4
  • Conference Article
  • Citations5

A Survey on Loss Functions for Deep Face Recognition Network

  • Sep 08, 2021
  • Aly Khalifa +1
  • Research Article
  • Citations8

DGFaceNet: Lightweight and efficient face recognition

  • Jun 27, 2023
  • Engineering Applications of Artificial Intelligence
  • Feng Zhao +3
  • Research Article
  • Citations20

A sample‐proxy dual triplet loss function for object re‐identification

  • Jul 25, 2022
  • IET Image Processing
  • Hanxiao Wu +5
  • Research Article
  • Citations6

More discriminative convolutional neural network with inter-class constraint for classification

  • May 01, 2018
  • Computers & Electrical Engineering
  • Jianchao Fei +4
  • Conference Article
  • Citations3134

CosFace: Large Margin Cosine Loss for Deep Face Recognition

  • Jun 01, 2018
  • Hao Wang +7
  • Book Chapter
  • Citations1

A Discriminative Feature Learning Based on Deep Residual Network for Face Verification

  • Jan 01, 2018
  • Tong Zhang +2
  • PDF
  • Research Article
  • Citations4

Chasing a Better Decision Margin for Discriminative Histopathological Breast Cancer Image Classification

  • Oct 20, 2023
  • Electronics
  • Pendar Alirezazadeh +2
  • Conference Article
  • Citations2

Fisher Loss: A More Discriminative Feature Learning Method in Classification

  • Jul 01, 2019
  • Yuhang Ye +2
  • Research Article
  • Citations21

Improved softmax loss for deep learning‐based face and expression recognition

  • Nov 27, 2019
  • Cognitive Computation and Systems
  • Jiancan Zhou +4
  • Research Article
  • Citations37

Face Recognition Depends on Specialized Mechanisms Tuned to View-Invariant Facial Features: Insights from Deep Neural Networks Optimized for Face or Object Recognition.

  • Sep 01, 2021
  • Cognitive Science
  • Naphtali Abudarham +2
  • Research Article
  • Citations15

A loss combination based deep model for person re-identification

  • Jul 08, 2017
  • Multimedia Tools and Applications
  • Fuqing Zhu +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.