Spherical Confidence Learning for Face Recognition, accepted to CVPR2021.

Related tags

Deep Learning SCF
Overview

Sphere Confidence Face (SCF)

This repository contains the PyTorch implementation of Sphere Confidence Face (SCF) proposed in the CVPR2021 paper: Shen Li, Xu Jianqing, Xiaqing Xu, Pengcheng Shen, Shaoxin Li, and Bryan Hooi. Spherical Confidence Learning for Face Recognition, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021 with Appendices.

Empirical Results

IJB-B ResNet100 1e-5 ResNet100 1e-4 IJB-C ResNet100 1e-5 ResNet100 1e-4
CosFace 89.81 94.59 CosFace 93.86 95.95
+ PFE-G 89.96 94.64 + PFE-G 94.09 96.04
+ PFE-v N/A N/A + PFE-v N/A N/A
+ SCF-G 89.97 94.56 + SCF-G 94.15 96.02
+ SCF 91.02 94.95 + SCF 94.78 96.22
ArcFace 89.33 94.20 ArcFace 93.15 95.60
+ PFE-G 89.55 94.30 + PFE-G 92.95 95.32
+ PFE-v N/A N/A + PFE-v N/A N/A
+ SCF-G 89.52 94.24 + SCF-G 93.85 95.33
+ SCF 90.68 94.74 + SCF 94.04 96.09

Requirements

  • python==3.6.0
  • torch==1.6.0
  • torchvision==0.7.0
  • tensorboard==2.4.0

Getting Started

Training

Training consists of two separate steps:

  1. Train ResNet100 imported from backbones.py as the deterministic backbone using spherical loss, e.g. ArcFace loss.
  2. Train SCF based on the pretrained backbone by specifying the arguments including [GPU_IDS], [OUTPUT_DIR], [PATH_BACKBONE_CKPT] (the path of the pretrained backbone checkpoint) and [PATH_FC_CKPT] (the path of the pretrained fc-layer checkpoint) and then running the command:
python train.py \
    --dataset "ms1m" \
    --seed 777 \
    --gpu_ids [GPU_IDS] \
    --batch_size 1024 \
    --output_dir [OUTPUT_DIR] \
    --saved_bkb [PATH_BACKBONE_CKPT] \
    --saved_fc [PATH_FC_CKPT] \
    --num_workers 8 \
    --epochs 30 \
    --lr 3e-5 \
    --lr_scheduler "StepLR" \
    --step_size 2 \
    --gamma 0.5 \
    --convf_dim 25088 \
    --z_dim 512 \
    --radius 64 \
    --max_grad_clip 0 \
    --max_grad_norm 0 \
    --tensorboard

Test

IJB benchmark: use $\kappa$ as confidence score for each face image to aggregate representations as in Eqn (14). Refer to the standard IJB benchmark for implementation.

1v1 verification benchmark: use Eqn (13) as the similarity score.

Other Implementations

SCF in TFace: SCF

Citation

@inproceedings{li2021spherical,
  title={Spherical Confidence Learning for Face Recognition},
  author={Li, Shen and Xu, Jianqing and Xu, Xiaqing and Shen, Pengcheng and Li, Shaoxin and Hooi, Bryan},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={15629--15637},
  year={2021}
}
You might also like...
The implementation of the CVPR2021 paper "Structure-Aware Face Clustering on a Large-Scale Graph with 10^7 Nodes"

STAR-FC This code is the implementation for the CVPR 2021 paper "Structure-Aware Face Clustering on a Large-Scale Graph with 10^7 Nodes" 🌟 🌟 . 🎓 Re

Shuai Shen 87 Dec 28, 2022
Learning Confidence for Out-of-Distribution Detection in Neural Networks
Learning Confidence for Out-of-Distribution Detection in Neural Networks

Learning Confidence Estimates for Neural Networks This repository contains the code for the paper Learning Confidence for Out-of-Distribution Detectio

null 235 Jan 5, 2023
Outlier Exposure with Confidence Control for Out-of-Distribution Detection
Outlier Exposure with Confidence Control for Out-of-Distribution Detection

OOD-detection-using-OECC This repository contains the essential code for the paper Outlier Exposure with Confidence Control for Out-of-Distribution De

Nazim Shaikh 64 Nov 2, 2022
the code for paper "Energy-Based Open-World Uncertainty Modeling for Confidence Calibration"

EOW-Softmax This code is for the paper "Energy-Based Open-World Uncertainty Modeling for Confidence Calibration". Accepted by ICCV21. Usage Commnd exa

Yezhen Wang 36 Dec 2, 2022
Training Confidence-Calibrated Classifier for Detecting Out-of-Distribution Samples / ICLR 2018

Training Confidence-Calibrated Classifier for Detecting Out-of-Distribution Samples This project is for the paper "Training Confidence-Calibrated Clas

null 168 Nov 29, 2022
Source code of NeurIPS 2021 Paper ''Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration''

CaGCN This repo is for source code of NeurIPS 2021 paper "Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration". Paper L

null 6 Dec 19, 2022
Code for "The Box Size Confidence Bias Harms Your Object Detector"

The Box Size Confidence Bias Harms Your Object Detector - Code Disclaimer: This repository is for research purposes only. It is designed to maintain r

Johannes G. 24 Dec 7, 2022
Pynomial - a lightweight python library for implementing the many confidence intervals for the risk parameter of a binomial model

Pynomial - a lightweight python library for implementing the many confidence intervals for the risk parameter of a binomial model

Demetri Pananos 9 Oct 4, 2022
Improving Calibration for Long-Tailed Recognition (CVPR2021)
Improving Calibration for Long-Tailed Recognition (CVPR2021)

MiSLAS Improving Calibration for Long-Tailed Recognition Authors: Zhisheng Zhong, Jiequan Cui, Shu Liu, Jiaya Jia [arXiv] [slide] [BibTeX] Introductio

Jia Research Lab 116 Dec 20, 2022
Comments
  • incorrect formula about Bessel functions of the first kind

    incorrect formula about Bessel functions of the first kind

    Hi expert, The backward function is (self.v) / z not (self.v + z) / z) which reference by https://functions.wolfram.com/Bessel-TypeFunctions/BesselJ/20/01/02/0001/

    https://github.com/MathsShen/SCF/blob/842fa96f6215b95a674fd4b48214274ea0209d90/ive.py#L34

    opened by BossunWang 0
Owner
Maths
Maths
GitHub
Face-Recognition-Attendence-System - This face recognition Attendence system using Python

Face-Recognition-Attendence-System I have developed this face recognition Attend

Riya Gupta 4 May 10, 2022
HGCAE Pytorch implementation. CVPR2021 accepted.

Hyperbolic Graph Convolutional Auto-Encoders Accepted to CVPR2021 ?? Official PyTorch code of Unsupervised Hyperbolic Representation Learning via Mess

Junho Cho 37 Nov 13, 2022
A spherical CNN for weather forecasting

DeepSphere-Weather - Deep Learning on the sphere for weather/climate applications. The code in this repository provides a scalable and flexible framew

DeepSphere 47 Dec 25, 2022
Spherical CNNs

Spherical CNNs Equivariant CNNs for the sphere and SO(3) implemented in PyTorch Overview This library contains a PyTorch implementation of the rotatio

Jonas Köhler 893 Dec 28, 2022
This is code to fit per-pixel environment map with spherical Gaussian lobes, using LBFGS optimization

Spherical Gaussian Optimization This is code to fit per-pixel environment map with spherical Gaussian lobes, using LBFGS optimization. This code has b

null 41 Dec 14, 2022
Code for PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Relighting and Material Editing

PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Relighting and Material Editing CVPR 2021. Project page: https://kai-46.github.io/

Kai Zhang 141 Dec 14, 2022
DVG-Face: Dual Variational Generation for Heterogeneous Face Recognition, TPAMI 2021

DVG-Face: Dual Variational Generation for HFR This repo is a PyTorch implementation of DVG-Face: Dual Variational Generation for Heterogeneous Face Re

null 52 Dec 30, 2022
Face Library is an open source package for accurate and real-time face detection and recognition

Face Library Face Library is an open source package for accurate and real-time face detection and recognition. The package is built over OpenCV and us

null 52 Nov 9, 2022
A large-scale face dataset for face parsing, recognition, generation and editing.

CelebAMask-HQ [Paper] [Demo] CelebAMask-HQ is a large-scale face image dataset that has 30,000 high-resolution face images selected from the CelebA da

switchnorm 1.7k Dec 26, 2022
Disentangled Face Attribute Editing via Instance-Aware Latent Space Search, accepted by IJCAI 2021.

Instance-Aware Latent-Space Search This is a PyTorch implementation of the following paper: Disentangled Face Attribute Editing via Instance-Aware Lat

null 67 Dec 21, 2022