Face Identification
41 papers with code • 4 benchmarks • 5 datasets
Face identification is the task of matching a given face image to one in an existing database of faces. It is the second part of face recognition (the first part being detection). It is a one-to-many mapping: you have to find an unknown person in a database to find who that person is.
Benchmarks
These leaderboards are used to track progress in Face Identification
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Face Identification models and implementations
MS-Celeb-1M
MegaFace
IJB-A
IJB-B
LTFT
Most implemented papers
MarginDistillation: distillation for margin-based softmax
david-svitov/margindistillation
•
•
The usage of convolutional neural networks (CNNs) in conjunction with a margin-based softmax approach demonstrates a state-of-the-art performance for the face recognition problem.
SL-DML: Signal Level Deep Metric Learning for Multimodal One-Shot Action Recognition
raphaelmemmesheimer/sl-dml
•
•
Further, we show that our approach generalizes well in experiments on the UTD-MHAD dataset for inertial, skeleton and fused data and the Simitate dataset for motion capturing data.
Key-Nets: Optical Transformation Convolutional Networks for Privacy Preserving Vision Sensors
visym/keynet
•
•
Modern cameras are not designed with computer vision or machine learning as the target application.
BroadFace: Looking at Tens of Thousands of People at Once for Face Recognition
kakaoenterprise/BroadFace
•
•
ECCV 2020
Moreover, we propose a novel compensation method to increase the number of referenced instances in the training stage.
Improvising the Learning of Neural Networks on Hyperspherical Manifold
barulalithb/stereo-angular-margin
•
•
First, the stereographic projection is implied to transform data from Euclidean space ($\mathbb{R}^{n}$) to hyperspherical manifold ($\mathbb{S}^{n}$) to analyze the performance of angular margin losses.
Measuring Hidden Bias within Face Recognition via Racial Phenotypes
seymayucer/facialphenotypes
•
•
We use the set of observable characteristics of an individual face where a race-related facial phenotype is hence specific to the human face and correlated to the racial profile of the subject.
DeepFace-EMD: Re-ranking Using Patch-wise Earth Mover's Distance Improves Out-Of-Distribution Face Identification
anguyen8/deepface-emd
•
•
CVPR 2022
Face identification (FI) is ubiquitous and drives many high-stake decisions made by law enforcement.
Open-Set Face Identification on Few-Shot Gallery by Fine-Tuning
1ho0jin1/osfi-by-finetuning
•
•
In this paper, we focus on addressing the open-set face identification problem on a few-shot gallery by fine-tuning.
Learning Unified Representations for Multi-Resolution Face Recognition
As per the input, a resolution-specific BNet is used and the output are implanted as feature maps in the feature pyramid of TNet, at a layer with the same resolution.
Fast and Interpretable Face Identification for Out-Of-Distribution Data Using Vision Transformers
DeepFace-EMD (Phan et al. 2022) reaches state-of-the-art accuracy on out-of-distribution data by first comparing two images at the image level, and then at the patch level.
