Face Verification
121 papers with code • 20 benchmarks • 21 datasets
Face Verification is a machine learning task in computer vision that involves determining whether two facial images belong to the same person or not. The task involves extracting features from the facial images, such as the shape and texture of the face, and then using these features to compare and verify the similarity between the images.
( Image credit: Pose-Robust Face Recognition via Deep Residual Equivariant Mapping )
Benchmarks
These leaderboards are used to track progress in Face Verification
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Face Verification models and implementations
LFW
CASIA-WebFace
MS-Celeb-1M
CK+
IJB-C
MegaFace
IJB-A
IJB-B
VGG Face
Oulu-CASIA
Most implemented papers
Deep Face Recognition: A Survey
Deep learning applies multiple processing layers to learn representations of data with multiple levels of feature extraction.
Partial FC: Training 10 Million Identities on a Single Machine
The experiment demonstrates no loss of accuracy when training with only 10\% randomly sampled classes for the softmax-based loss functions, compared with training with full classes using state-of-the-art models on mainstream benchmarks.
Sampling Matters in Deep Embedding Learning
CompVis/metric-learning-divide-and-conquer
•
•
ICCV 2017
In addition, we show that a simple margin based loss is sufficient to outperform all other loss functions.
SeesawFaceNets: sparse and robust face verification model for mobile platform
didi/AoE
•
•
arXiv 2019
Therefore, designing lightweight networks with low memory requirement and computational cost is one of the most practical solutions for face verification on mobile platform.
Face Detection with End-to-End Integration of a ConvNet and a 3D Model
tfwu/FaceDetection-ConvNet-3D
•
•
The proposed method addresses two issues in adapting state- of-the-art generic object detection ConvNets (e. g., faster R-CNN) for face detection: (i) One is to eliminate the heuristic design of prede- fined anchor boxes in the region proposals network (RPN) by exploit- ing a 3D mean face model.
Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Network
The 3D shapes of faces are well known to be discriminative.
FacePoseNet: Making a Case for Landmark-Free Face Alignment
Instead, we compare our FPN with existing methods by evaluating how they affect face recognition accuracy on the IJB-A and IJB-B benchmarks: using the same recognition pipeline, but varying the face alignment method.
Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC
In each iteration, positive class centers and a random subset of negative class centers are selected to compute the margin-based softmax loss.
AdaFace: Quality Adaptive Margin for Face Recognition
mk-minchul/adaface
•
•
CVPR 2022
In this work, we introduce another aspect of adaptiveness in the loss function, namely the image quality.
GhostFaceNets: Lightweight Face Recognition Model From Cheap Operations
HamadYA/GhostFaceNets
•
•
IEEE Access 2023
The development of deep learning-based biometric models that can be deployed on devices with constrained memory and computational resources has proven to be a significant challenge.
