WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition

In this paper, we contribute a new million-scale face benchmark containing noisy 4M identities/260M faces (WebFace260M) and cleaned 2M identities/42M faces (WebFace42M) training data, as well as an elaborately designed time-constrained evaluation protocol. Firstly, we collect 4M name list and download 260M faces from the Internet... (read more)

PDF Abstract
No code implementations yet. Submit your code now

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper


METHOD TYPE
Depthwise Convolution
Convolutions
Pointwise Convolution
Convolutions
Softmax
Output Functions
Depthwise Separable Convolution
Convolutions
Max Pooling
Pooling Operations
Average Pooling
Pooling Operations
Residual Block
Skip Connection Blocks
Grouped Convolution
Convolutions
Sigmoid Activation
Activation Functions
Global Average Pooling
Pooling Operations
SENet
Convolutional Neural Networks
Dense Connections
Feedforward Networks
Swish
Activation Functions
Inverted Residual Block
Skip Connection Blocks
ResNeXt Block
Skip Connection Blocks
RMSProp
Stochastic Optimization
Batch Normalization
Normalization
ReLU
Activation Functions
Dropout
Regularization
Squeeze-and-Excitation Block
Image Model Blocks
1x1 Convolution
Convolutions
EfficientNet
Image Models
Bottleneck Residual Block
Skip Connection Blocks
Convolution
Convolutions
Residual Connection
Skip Connections
ResNet
Convolutional Neural Networks
Kaiming Initialization
Initialization
ResNeXt
Convolutional Neural Networks